List of AMD graphics processing units

The following is a list that contains general information about GPUs and video cards made by AMD, including those made by ATI Technologies before 2006, based on official specifications in table-form.

Field explanations

The headers in the table listed below describe the following:

• Model – The marketing name for the GPU assigned by AMD/ATI. Note that ATI trademarks have been replaced by AMD trademarks starting with the Radeon HD 6000 series for desktop and AMD FirePro series for professional graphics.
• Codename – The internal engineering codename for the GPU.
• Launch – Date of release for the GPU.
• Architecture – The microarchitecture used by the GPU.
• Fab – Fabrication process. Average feature size of components of the GPU.
• Transistors – Number of transistors on the die.
• Die size – Physical surface area of the die.
• Core config – The layout of the graphics pipeline, in terms of functional units.
• Core clock – The reference base and boost (if available) core clock frequency.
• Fillrate
  • Pixel - The rate at which pixels can be rendered by the raster operators to a display. Measured in pixels/s.
  • Texture - The rate at which textures can be mapped by the texture mapping units onto a polygon mesh. Measured in texels/s.
• Performance
  • Shader operations - How many operations the pixel shaders (or unified shaders in Direct3D 10 and newer GPUs) can perform. Measured in operations/s.
  • Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to Direct3D 9.0c and older GPUs). Measured in vertices/s.
• Memory
  • Bus type – Type of memory bus utilized.
  • Bus width – Maximum bit width of the memory bus utilized.
  • Size – Size of the graphics memory.
  • Clock – The reference memory clock frequency.
  • Bandwidth – Maximum theoretical memory bandwidth based on bus type and width.
• TDP (Thermal design power) – Maximum amount of heat generated by the GPU chip, measured in Watt.
• TBP (Typical board power) – Typical power drawn by the total board, including power for the GPU chip and peripheral equipment, such as Voltage regulator module, memory, fans, etc., measured in Watt.
• Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCIe).
• API support – Rendering and computing APIs supported by the GPU and driver.

Due to conventions changing over time, some numerical definitions such as core config, core clock, performance and memory should not be compared one-to-one across generations. The following tables are for reference use only, and do not reflect actual performance.

Video codec acceleration

• R100 – Video Immersion
• R200 – Video Immersion II
• R300 – Video Immersion II + Video Shader
• R410 – Video Shader HD
• R420 – Video Shader HD + DXVA
• R520 – Avivo Video
• R600 – Avivo HD – UVD 1.0
• R700 – UVD 2, UVD 2.2
• Evergreen – UVD 2.2
• Northern Islands – UVD 3 (HD 67xx UVD 2.2)
• Southern Islands – UVD 3.1, VCE 1.0
• Sea Islands – UVD 4.2, VCE 2.0
• Volcanic Islands – UVD 5.0, 6.0, VCE 3.0
• Arctic Islands – UVD 6.3, VCE 3.4
• Vega – UVD 7.0, VCE 4.0 and VCN 1.0 only at AMD Raven Ridge
• Navi 1X – VCN 2.0
• Navi 2X – VCN 3.0
• Navi 3X – VCN 3.0

Features overview

The following table shows features of AMD/ATI's GPUs.

[ VisualEditor ]

• view
• talk
• edit

Name of GPU series	Wonder	Mach	3D Rage	Rage Pro	Rage 128	R100	R200	R300	R400	R500	R600	RV670	R700	Evergreen	Northern Islands		Southern Islands	Sea Islands	Volcanic Islands	Arctic Islands/Polaris	Vega	Navi 1x	Navi 2x	Navi 3x	Navi 4x
Released	1986	1991	Apr 1996	Mar 1997	Aug 1998	Apr 2000	Aug 2001	Sep 2002	May 2004	Oct 2005	May 2007	Nov 2007	Jun 2008	Sep 2009	Oct 2010	Dec 2010	Jan 2012	Sep 2013	Jun 2015	Jun 2016, Apr 2017, Aug 2019	Jun 2017, Feb 2019	Jul 2019	Nov 2020	Dec 2022	Feb 2025
Marketing Name	Wonder	Mach	3D Rage	Rage Pro	Rage 128	Radeon 7000	Radeon 8000	Radeon 9000	Radeon X700/X800	Radeon X1000	Radeon HD 2000	Radeon HD 3000	Radeon HD 4000	Radeon HD 5000	Radeon HD 6000		Radeon HD 7000	Radeon 200	Radeon 300	Radeon 400/500/600	Radeon RX Vega, Radeon VII	Radeon RX 5000	Radeon RX 6000	Radeon RX 7000	Radeon RX 9000
AMD support
Kind	2D		3D
Instruction set architecture	Not publicly known										TeraScale instruction set						GCN instruction set					RDNA instruction set
Microarchitecture	Not publicly known					GFX1		GFX2			TeraScale 1 (VLIW5) (GFX3)			TeraScale 2 (VLIW5) (GFX4)	TeraScale 2 (VLIW5) up to 68xx (GFX4)	TeraScale 3 (VLIW4) in 69xx [1][2] (GFX5)	GCN 1st gen (GFX6)	GCN 2nd gen (GFX7)	GCN 3rd gen (GFX8)	GCN 4th gen (GFX8)	GCN 5th gen (GFX9)	RDNA (GFX10.1)	RDNA 2 (GFX10.3)	RDNA 3 (GFX11)	RDNA 4 (GFX12)
Type	Fixed pipeline[a]						Programmable pixel & vertex pipelines				Unified shader model
Direct3D	—		5.0	6.0		7.0	8.1	9.0 11 (9_2)	9.0b 11 (9_2)	9.0c 11 (9_3)	10.0 11 (10_0)	10.1 11 (10_1)		11 (11_0)			11 (11_1) 12 (11_1)	11 (12_0) 12 (12_0)			11 (12_1) 12 (12_1)		11 (12_1) 12 (12_2)
Shader model	—						1.4	2.0+	2.0b	3.0	4.0	4.1		5.0			5.1	5.1 6.5			6.7				6.8
OpenGL	—			1.1	1.2	1.3		1.5[b][3]			3.3			4.6[4][c]
Vulkan	—															1.1[c][d]	1.3[5]		1.4[6]
OpenCL	—										Close to Metal		1.1 (not supported by Mesa)	1.2+ (on Linux: 1.1+ (no Image support on Clover, with by Rusticl) with Mesa, 1.2+ on GCN 1.Gen)				2.0+ (Adrenalin driver on Win7+) (on Linux ROCm, Mesa 1.2+ (no Image support in Clover, but in Rusticl with Mesa, 2.0+ and 3.0 with AMD drivers or AMD ROCm), 5th gen: 2.2 win 10+ and Linux RocM 5.0+				2.2+ and 3.0 Windows 8.1+ and Linux ROCm 5.0+ (Mesa Rusticl 1.2+ and 3.0 (2.1+ and 2.2+ wip))[7][8][9]
HSA / ROCm	—																					?
Video decoding ASIC	—										Avivo/UVD	UVD+	UVD 2	UVD 2.2	UVD 3		UVD 4	UVD 4.2	UVD 5.0 or 6.0	UVD 6.3	UVD 7 [10][e]	VCN 2.0 [10][e]	VCN 3.0 [11]	VCN 4.0	VCN 5.0
Video encoding ASIC	—																VCE 1.0	VCE 2.0	VCE 3.0 or 3.1	VCE 3.4	VCE 4.0 [10][e]
Fluid Motion [f]																								?
Power saving	?										PowerPlay				PowerTune		PowerTune & ZeroCore Power					?
TrueAudio	—																	Via dedicated DSP		Via shaders
FreeSync	—																	1 2
HDCP[g]	—										?							1.4		2.2		2.3 [12]
PlayReady[g]	—																			3.0		3.0
Supported displays[h]						1–2	2							2–6								?			4
Max. resolution	?													2–6 × 2560×1600			2–6 × 4096×2160 @ 30 Hz			2–6 × 5120×2880 @ 60 Hz	3 × 7680×4320 @ 60 Hz [13]	7680×4320 @ 60 Hz PowerColor		7680x4320 @165 Hz	7680x4320
/drm/radeon[i]																			—
/drm/amdgpu[i]	—																	Optional [14]

1. The Radeon 100 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
2. R300, R400 and R500 based cards do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power of two (NPOT) textures.
3. OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.
4. Vulkan support is theoretically possible but has not been implemented in a stable driver.
5. The UVD and VCE were replaced by the Video Core Next (VCN) ASIC in the Raven Ridge APU implementation of Vega.
6. Video processing for video frame rate interpolation technique. In Windows it works as a DirectShow filter in your player. In Linux, there is no support on the part of drivers and / or community.
7. To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
8. More displays may be supported with native DisplayPort connections, or splitting the maximum resolution between multiple monitors with active converters.
9. DRM (Direct Rendering Manager) is a component of the Linux kernel. AMDgpu is the Linux kernel module. Support in this table refers to the most current version.

API overview

The following table shows the graphics and compute APIs support across ATI/AMD GPU microarchitectures. Note that a branding series might include older generation chips.

[ VisualEditor ]

• view
• talk
• edit

Chip series	Micro­architecture	Fab	Supported APIs					AMD support	Year introduced	Introduced with
			Rendering			Computing / ROCm
			Vulkan[15]	OpenGL[16]	Direct3D	HSA	OpenCL
Wonder	Fixed-pipeline[a]	1000 nm 800 nm	—	—	—	—	—	Ended	1986	Graphics Solutions
Mach		800 nm 600 nm							1991	Mach8
3D Rage		500 nm			5.0				1996	3D Rage
Rage Pro		350 nm		1.1	6.0				1997	Rage Pro
Rage 128		250 nm		1.2					1998	Rage 128 GL/VR
R100		180 nm 150 nm		1.3	7.0				2000	Radeon
R200	Programmable pixel & vertex pipelines	150 nm			8.1				2001	Radeon 8500
R300		150 nm 130 nm 110 nm		2.0[b]	9.0 11 (FL 9_2)				2002	Radeon 9700
R420		130 nm 110 nm			9.0b 11 (FL 9_2)				2004	Radeon X800
R520		90 nm 80 nm			9.0c 11 (FL 9_3)				2005	Radeon X1800
R600	TeraScale 1	80 nm 65 nm		3.3	10.0 11 (FL 10_0)		ATI Stream		2007	Radeon HD 2900 XT
RV670		55 nm			10.1 11 (FL 10_1)		ATI Stream APP[17]			Radeon HD 3850/3870
RV770		55 nm 40 nm					1.0		2008	Radeon HD 4850/4870
Evergreen	TeraScale 2	40 nm		4.5 (Linux 4.2) [18][19][20][c]	11 (FL 11_0)		1.2		2009	Radeon HD 5850/5870
Northern Islands	TeraScale 2 TeraScale 3								2010	Radeon HD 6850/6870 Radeon HD 6950/6970
Southern Islands	GCN 1st gen	28 nm	1.0	4.6	11 (FL 11_1) 12 (FL11_1)		1.2 2.0 possible		2012	Radeon HD 7950/7970
Sea Islands	GCN 2nd gen		1.2		11 (FL 12_0) 12 (FL 12_0)		2.0 (1.2 in MacOS, Linux) 2.1 Beta in Linux ROCm 2.2 possible		2013	Radeon HD 7790
Volcanic Islands	GCN 3rd gen								2014	Radeon R9 285
Arctic Islands	GCN 4th gen	28 nm 14 nm	1.2 1.4 (GCN 4)					Supported	2016	Radeon RX 480
Polaris									2017	Radeon 520/530 Radeon RX 530/550/570/580
Vega	GCN 5th gen	14 nm 7 nm	1.4		11 (FL 12_1) 12 (FL 12_1)				2017	Radeon Vega Frontier Edition
Navi	RDNA	7 nm							2019	Radeon RX 5700 (XT)
Navi 2x	RDNA 2	7 nm 6 nm			11 (FL 12_1) 12 (FL 12_2)				2020	Radeon RX 6800 (XT)
Navi 3x	RDNA 3	6 nm 5 nm							2022	Radeon RX 7900 XT(X)
Navi 4x	RDNA 4	4 nm							2025	Radeon RX 9070 (XT)

1. Radeon 7000 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
2. These series do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power-of-two (NPOT) textures.
3. OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.

^[21][22][23]

Desktop GPUs

Wonder series

Main article: ATI Wonder series

Model	Launch	Fab (nm)	Bus interface	Memory
				Size (KiB)	Bus type	Bus width (bit)
Wonder MDA/CGA	1986	1000	PC/XT	64	DRAM	8
Wonder EGA	1987		PC/XT	256
Wonder VGA	1987	1000, 800	PC/XT, ISA	256, 512 1024		8, 16

Mach series

Main article: ATI Mach

Model	Launch	Fab (nm)	Bus interface	Memory
				Size (KiB)	Bus type	Bus width (bit)
Mach 8	1991	800	ISA, MCA	512, 1024	DRAM, VRAM	32
Mach 32	1992		ISA, EISA, VLB, PCI, MCA	1024, 2048	DRAM, VRAM	64
Mach 64 CX	1994	700	ISA, VLB, PCI	1024, 2048, 4096	DRAM, VRAM
Mach 64 GX
Mach 64 CT	1995	600	PCI		DRAM, VRAM, EDO
Mach 64 VT (264VT)
Mach 64 VT2 (264VT2)	1996				EDO
Mach 64 VT4 (264VT4)	1998			2048, 4096	EDO, SGRAM

Rage series

Main article: ATI Rage

Model	Launch	GPU arch	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (FLOPS)	TDP (Watts)	API compliance
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)			Direct3D	OpenGL
3D Rage	April 1996[24]	Mach64	500	PCI	40	40	1:0:1:1	40	40	40	0	2	0.32	EDO	64	?	?	5.0	None2
3D Rage II	September 1996	Mach64 (Rage2 for Rage IIc)		AGP 1× (Rage IIc only), PCI	60	83 (66 MHz with EDO)		60	60	60		2, 4, 8	0.664	EDO, SGRAM, SDR		?	?
Rage Pro	March 1997	Rage 3	350	AGP 1x, AGP 2×, PCI	75	75		75	75	75		4, 8, 16	0.6			?	6	6.0	1.1
Rage XL[25][26][27][28]	August 1998		250	AGP 2×, PCI	83	125		83	83	83		8	1.0	SDR		?	9
Rage 128 VR		Rage 4			80	120	2:0:2:2	160	160	160		8, 32	0.96			?	?		1.2
Rage 128 GL					103	103		206	206	206		16, 32	1.648	SGRAM, SDR	128	?	?
Rage 128 Pro	August 1999			AGP 4×, PCI	125	143		250	250	250			2.288			?	5
Rage 128 Ultra					130	130		260	260	260		16, 32	2.088	SDR		?	?
Rage Fury MAXX	October 1999			AGP 4×	125	143	2:0:2:2 ×2	500	500	500		32 ×2	4.576		128 ×2	?	?

¹ Pixel pipelines : Vertex shaders : Texture mapping units : Render output units
² OpenGL 1.0 (Generic 2D) is provided through software implementations.

Radeon R100 series

Main article: Radeon R100 series

• All models include Direct3D 7.0 and OpenGL 1.3
• The R100 cards were originally launched without any numbering as Radeon SDR, DDR, LE and VE; these products were later "rebranded" to their names within the numbered naming scheme, when the Radeon 8000 series was introduced.

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (FLOPS)	TDP (Watts)
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon VE / Radeon 7000	February 19, 2001	RV100 (piglet)	180	AGP 4x, PCI	150/166/183	150/166/183	1:0:3:1	183 (max)	336 (max)	549 (max)	0	32, 64	2.688 (max)	DDR	64	?	10
Radeon LE / Radeon 7100 (OEM)	April 6, 2001[29]	Rage 6 / R100		AGP 4x	150	150	2:1:6:2	296	296	888	37.5	32	4.736		128	?	11
Radeon SDR / Radeon 7200 (SDR)	June 1, 2000			AGP 4x, PCI	166	166		333	333	996	41.5		2.656	SDR		?	14
Radeon DDR / Radeon 7200 (DDR)	April 1, 2000			AGP 4x	166/183A	166/183A		333/366A	333/366A	966/1098A	41.5/45.75A	32, 64	5.312/5.856A	DDR		?	13
Radeon DDR / Radeon 7200 VIVO	2001			AGP 4x, PCI	166/183B	166/183B		333/366B	333/366B	966/1098B	41.5/45.75B	64	5.312/5.856B			?	17
Radeon DDR / Radeon 7500 VIVO "SE"					200	200		400	400	1200	50.0		6.400			?	20
Radeon 7500 LE		RV200 (morpheus)	150		250	175		500	500	1500	62.5	32, 64	5.600		64 128	?	21
Radeon 7500	August 14, 2001	RV200 (morpheus)			290	230		580	580	1740	72.5	32, 64, 128[30]	7.360		128	?	23

¹ Pixel pipelines : Vertex shaders : Texture mapping units : Render output units

^A First number indicates cards with 32 MB of memory. Second number indicates cards with 64 MB of memory.
^B First number indicates OEM cards. Second number indicates Retail cards.

IGP (3xx series)

• All models are manufactured with a 180 nm fabrication process
• All models include Direct3D 7.0 and OpenGL 1.3
• Based on the Radeon VE

Model	Launch	Code name	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon 320	May 2002	A3	FSB	160	200, 266	1:0:3:1	160	160	480	0	?	1.6, 2.128	DDR	64
Radeon 330	2002	RS200L (wilma)		150			150	150	450
Radeon 340		RS200 (wilma)		183			183	183	549

¹ Pixel pipelines : Vertex shaders : Texture mapping units : Render output units

Radeon R200 series

Main article: Radeon R200 series

• All models are manufactured with a 150 nm fabrication process
• All models include Direct3D 8.1 and OpenGL 1.4

Model	Launch	Code name	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (FLOPS)	TDP (Watts)
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon 8500	August 14, 2001	R200 (chaplin)	AGP 4×, PCI	275	275	4:2:8:4	1100	1100	2200	137.5	64, 128	8.8	DDR	128	?	33
Radeon 8500 LE	October 30, 2001			250	200 250		1000	1000	2000	125		8			?	?
Radeon 9000	August 1, 2002	RV250 (iris)			200	4:1:4:4			1000	50		6.4			?	?
Radeon 9000 Pro				275	275		1100	1100	1100	68.75		8.8			?	?
Radeon 9100	April 1, 2003	R200 (chaplin)		250	200 250	4:2:8:4	1000	1000	2000	125		8.0 4.0
														128 64	?	?
Radeon 9200		RV280 (argus)	AGP 8×, PCI		200	4:1:4:4			1000	62.5	64, 128, 256	6.4		128	?	?
Radeon 9200 SE	March 1, 2003			200	166		800	800	800	50		2.67		64	?	?
Radeon 9250	March 1, 2004			240	200		960	960	960	60		3.2, 6.4		64, 128	?	?
Radeon 9250 SE	2004		AGP 8x											64	?	?

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units

IGP (9000 series)

• All models are manufactured with a 150 nm fabrication process
• All models include Direct3D 8.1 and OpenGL 1.4
• Based on the Radeon 9200

Model	Launch	Code name	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon 9000	2003	RC350	FSB	300	400	4:1:2:2	600	600	600	75	16 - 128	3.2	DDR	64
Radeon 9100		RS300 (superman)										6.4		128
Radeon 9100 Pro	May 3, 2004	RS350

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units

Radeon R300 series

AGP (9000 series, X1000 series)

Main article: Radeon R300 series

• All models include Direct3D 9.0 and OpenGL 2.0
• All models use an AGP 8x interface

Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (GFLOPS)	TDP (Watts)
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon 9500	October 24, 2002	R300 (Khan)	150	275	270	4:4:4:4	1100	1100	1100	275	64, 128	8.64 17.28	DDR	128 256	?	29
Radeon 9500 Pro						8:4:8:8	2200	2200	2200		128	8.64		128	?	50
Radeon 9550	April-summer 2004	RV350 (Shivah)	130	250	200	4:2:4:4	1000	1000	1000	125	64, 128, 256	6.4			?	?
Radeon 9550 SE												3.2		64	?	?
Radeon 9600	2003			325			1300	1300	1300	162.5	128, 256	6.4		128	?	17
Radeon 9600 Pro	March 6, 2003			400	300		1600	1600	1600	200		9.6			?	19
Radeon 9600 SE	2003			325	200		1300	1300	1300	162.5	64, 128, 256	3.2		64	?	?
Radeon 9600 XT	September 30, 2003	RV360		500	300		2000	2000	2000	250	128, 256	9.6		128	?	20
Radeon 9600 TX	2003 (Medion OEM)	R300 (Khan)	150	297	270	8:4:8:8	2376	2376	2376	287	128	8.6			?	?
Radeon 9700 TX	2002 (Dell OEM)			263	263		2104	2104	2104	275		16.83		256	?	?
Radeon 9700	October 24, 2002			275	270		2200	2200	2200			17.28			?	42
Radeon 9700 Pro	July 18, 2002			325	310		2600	2600	2600	325		19.84			?	50
Radeon 9800	2003	R350													?	40
Radeon 9800 XL				350			2800	2800	2800	350					?	?
Radeon 9800 XXL[31]	October 1, 2003	R360		390	338		3120	3120	3120	390		21.60		256[31]	?	?
Radeon 9800 Pro (R350)	March 1, 2003[32]	R350		380	340 (128 MB) 350 (256 MB)		3040	3040	3040	380	128 256	21.76 22.40	DDR GDDR2	256	?	53
Radeon 9800 Pro (R360)	2003	R360			340						128	21.76	DDR		?	51
Radeon 9800 SE[33]	March 1, 2003[34]	R350		325 380[33]	270 340[33]	4:4:4:4[34]	1300 1520[33]	1300 1520[33]	1300 1520[33]	325 380[33]	128 256	8.64 21.76[33]	DDR	128 2562[33]	?	50
Radeon 9800 XT	September 9, 2003	R360		412	365	8:4:8:8	3296	3296	3296	412	256	23.36		256	?	74
Radeon X1050 AGP	December 7, 2006	RV350 (Shivah)	130	250	200	4:2:4:4	1000	1000	1000	125	128, 256	6.4		128	?	?
Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Performance (GFLOPS)	TDP (Watts)
							Fillrate				Memory

¹ Pixel shaders : Vertex Shaders : Texture mapping units : Render output units
² The 256-bit version of the 9800 SE when unlocked to 8-pixel pipelines with third party driver modifications should function close to a full 9800 Pro.^[35]

PCIe (X3xx, X5xx, X6xx, X1000 series)

Main article: Radeon R300 series

• All models include Direct3D 9.0 and OpenGL 2.0
• All models use a PCIe ×16 interface

Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (GFLOPS)	TDP (Watts)
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon X300	September 1, 2004	RV370 (hari)	110	325	200	4:2:4:4	1300	1300	1300	162.5	64, 128	6.4	DDR	128	?	26
Radeon X300 LE															?	?
Radeon X300 SE												3.2		64	?	25
Radeon X300 SE HyperMemory	April 4, 2005				300						32, 64, 128 onboard + up to 128 system				?	?
Radeon X550	June 21, 2005			400	250		1600	1600	1600	200	128, 256	8 4		128 64	?	?
Radeon X550 HyperMemory											128, 256 onboard + up to 512 system				?	?
Radeon X600 SE	September 1, 2004			325			1300	1300	1300	162.5	128, 256	4		64	?	?
Radeon X600				400			1600	1600	1600	200		8		128	?	30
Radeon X600 Pro (RV370)					300							9.6			?	30
Radeon X600 Pro (RV380)		RV380 (vishnu)	130												?	31
Radeon X600 XT				500	370		2000	2000	2000	250		11.84			?	?
Radeon X1050 (RV370)	December 7, 2006	RV370 (hari)	110	400	250 333		1600	1600	1600	200		5.328	DDR DDR2	64 128	?	?

¹ Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

IGP (X2xx, 11xx series)

Main article: Radeon R300 series

• All models include Direct3D 9.0 and OpenGL 2.0
• Based on the Radeon X300

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon Xpress X200	November 8, 2004	RS480 (metallo)	130	HT	300	200-400 (DDR), 200 (sideport)	4:2:2:2	600	600	600	0	16-128 system + 16 sideport	1.6-6.4 system + 0.8 sideport	DDR	64, 128
Radeon Xpress 1100 (originally Xpress 200)	2005	RS482 (grayskull)	110	HT	300	200-400 (DDR), 400-800 (DDR2)						16-128 system	1.6- 12.8 system	DDR, DDR2
Radeon Xpress 1150 (originally Xpress 200 for Intel)	March 11, 2005 (Intel), May 23, 2006 (AMD)	RC400, RC410, RS400, RS415, RS485		HT, FSB	400			800	800	800			1.6-12.8

¹Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

Radeon R400 series

AGP (X7xx, X8xx)

Main article: Radeon R400 series

• All models include AGP 8×
• All models include Direct3D 9.0b and OpenGL 2.0

Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (FLOPS)	TDP (Watts)
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon X700	Mar 2005	RV410 (alto)	110	400	350	8:6:8:8	3200	3200	3200	600	128, 256	11.2	DDR	128	?	31
Radeon X700 Pro	Mar 1, 2005			425	432		3400	3400	3400	637.5		13.824	GDDR3		?	39
Radeon X800 SE	Oct 2004	R420 (loki)	130		400			6800			256	25.6		256	?	?
Radeon X800 GT	December 6, 2005			475	490	8:6:8:16	3800	7600	3800	712.5		31.36			?	35
Radeon X800	Dec. 2004	R430	110	400	350	12:6:12:16	4800	6400	4800	600		22.4			?	?
Radeon X800 GTO	December 6, 2005	R420 (loki)	130		490							31.36			?	31
Radeon X800 Pro	May 5, 2004			475	450		5700	7600	5700	712.5		28.8			?	49
Radeon X800 XL	February 2, 2005	R430	110	400	490	16:6:16:16	6400	6400	6400	600		31.36			?	57
Radeon X800 XT	May 4, 2004	R420 (loki)	130	500	500		8000	8000	8000	750		32			?	86
Radeon X800 XT PE				520	560		8320	8320	8320	780		35.84			?	87
Radeon X850 Pro	February 28, 2005	R481		507	520	12:6:12:16	6084	8112	6084	760.5		33.28			?	?
Radeon X850 XT				520	540	16:6:16:16	8320	8320	8320	780		34.56			?	86
Radeon X850 XT PE				540	590		8640	8640	8640	810		37.76			?	?

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units

PCIe (X5xx, X7xx, X8xx, X1000 series)

Main article: Radeon R400 series

• All models include PCIe ×16
• All models include Direct3D 9.0b and OpenGL 2.0

Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Performance (FLOPS)	TDP (Watts)
							MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon X550 XT	January 24, 2007	RV410 (alto)	110	400	300	4:6:4:8	1600	3200	1600	600	128	4.8 9.6	DDR GDDR3	64 128	?	?
Radeon X550 XTX						8:6:8:8	3200		3200						?	?
Radeon X700 SE	April 1, 2005				200 250	4:6:4:8	1600		1600		128	3.2	DDR	64	?	?
Radeon X700 LE	December 21, 2004				250	8:6:8:8	3200		3200		128	4			?	29
Radeon X1050 (RV410)	Jan, 25, 2008				200						128, 256	6.4		128	?	20
Radeon X700	Sept. 2005				250 350							8 11.2			?	31
Radeon X700 Pro	December 21, 2004			425	432		3400	3400	3400	637.5	128, 256	13.824	GDDR3		?	39
Radeon X700 XT	Never Released			475	525		3800	3800	3800	712.5	128, 256	16.8			?	38
Radeon X740 XL	March 7, 2005 (Medion OEM)			425	450		3400	3400	3400	637.5	128	14.4			?	34
Radeon X800 GT 128 MB	August 1, 2005	R423 R480 (thor)	130	475	175	8:6:8:16	3800	7600	3800	712.5	128	22.4	DDR	256	?	32
Radeon X800 GT 256 MB					490						256	31.36	GDDR3		?	35
Radeon X800	December 1, 2004	R430 (thor)	110	392	350	12:6:12:16	4704	6272	4704	588	128, 256	22.4			?	?
Radeon X800 GTO 128 MB	September 15, 2005	R423 R480 R430 (thor)	130 110	400			4800	6400	4800	600	128	22.4			?	30
Radeon X800 GTO 256 MB					490						256	31.36			?	31
Radeon X800 Pro	May 5, 2004	R423 (thor)	130	475	450		5700	7600	5700	712.5		28.8			?	49
Radeon X800 XL	December 1, 2004 (256 MB) May 4, 2005 (512 MB)	R430 (thor)	110	400	490	16:6:16:16	6400	6400	6400	600	256, 512	31.36			?	56
Radeon X800 XT	December 1, 2004	R423 (thor)	130	500	500		8000	8000	8000	750	256	32			?	83
Radeon X800 XT Platinum Edition	May 5, 2004			520	560		8320	8320	8320	780		35.84			?	88
Radeon X850 Pro	December 1, 2004	R480 (thor)		507	520	12:6:12:16	6084	8112	6084	760.5		33.28			?	?
Radeon X850 XT				520	540	16:6:16:16	8320	8320	8320	780		34.56			?	86
Radeon X850 XT CrossFire Master	September 29, 2004			520								34.56			?	?
Radeon X850 XT Platinum Edition	December 21, 2004			540	590		8640	8640	8640	810		37.76			?	?
Model	Launch	Code name	Fab (nm)	Core clock (MHz)	Memory clock (MHz)	Core config1	MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Performance (FLOPS)	TDP (Watts)
							Fillrate				Memory

¹ Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

IGP (X12xx, 21xx)

Main article: Radeon R400 series

• All models include Direct3D 9.0b and OpenGL 2.0
• Based on Radeon X700

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon Xpress X1200	February 28, 2007	RS690C (zeus)	80	HT 2.0	350	400 – 800	4:2:4:4	1400	1400	1400	175	256 – 512	6.4 – 12.8	DDR2	128
Radeon Xpress X1250	August 29, 2006 (Intel), February 28, 2007 (AMD)	RS600, RS690 (zeus)		FSB, HT 2.0	400			1600	1600	1600	200
Radeon Xpress 2100	March 4, 2008	RS740 (titan)	55	HT 2.0	500			2000	2000	2000	250

Radeon X1000 series

Main article: Radeon X1000 series

Note that ATI X1000 series cards (e.g. X1900) do not have Vertex Texture Fetch, hence they do not fully comply with the VS 3.0 model. Instead, they offer a feature called "Render to Vertex Buffer (R2VB)" that provides functionality that is an alternative Vertex Texture Fetch.

Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config	Fillrate				Memory				TDP (Watts)	API support (version)		Release Price (USD)
							Core (MHz)	Memory (MHz)		MOperations/s	MPixels/s	MVertices/s	MTexels/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Max.	Direct3D	OpenGL
Radeon X1300	October 5, 2005 (PCIe) December 1, 2005 (AGP)	RV515	90	107	100	AGP 8× PCI PCIe ×16	450	250	4:2:4:4	1800	1800	225	1800	128 256	8.0	DDR DDR2	128		9.0c	2.1	$99 (128MB) $129 (256 MB)
Radeon X1300 HyperMemory	October 5, 2005					PCIe ×16								128 256 512	4.0	DDR2	64				$
Radeon X1300 PRO	October 5, 2005 (PCIe) November 1, 2006 (AGP)					AGP 8× PCIe ×16	600	400		2400	2400	300	2400	128 256	12.8		128	31			$149
Radeon X1300 XT	August 12, 2006	RV530		157	150		500		12:5:4:4	6000	2000	625	2000					22			$89
Radeon X1550	January 8, 2007	RV516		107	100	AGP 8x PCI PCIe x16			4:2:4:4	2200	2200	275	2200	128 256 512				27			$
Radeon X1600 PRO	October 10, 2005	RV530		157	150	AGP 8× PCIe ×16		390 390–690	12:5:4:4	6000	2000	625	2000		12.48	DDR2 GDDR3		41			$149 (128MB) $199 (256 MB)
Radeon X1600 XT	October 10, 2005 (PCIe)						590	690		7080	2360	737.5	2360	256 512	22.08	GDDR3		42			$249
Radeon X1650	February 1, 2007						500	400		6000	2000	625	2000		12.8	DDR2					$
Radeon X1650 SE		RV516		105		PCIe ×16	635		4:2:4:4					256		DDR2					$
Radeon X1650 GT	May 1, 2007 (PCIe) October 1, 2007 (AGP)	RV560	80	330	230	AGP 8× PCIe x16	400		24:8:8:8	9600	3200	800	3200	256 512		GDDR3					$
Radeon X1650 PRO	August 23, 2006 (PCIe) October 15, 2006 (AGP)	RV535			131		600	700	12:5:4:4	7200	2400	750	2400		22.4			44			$99
Radeon X1650 XT	October 30, 2006	RV560			230		525		24:8:8:8	12600	4200	1050	4200					55			$149
Radeon X1700 FSC	November 5, 2007 (OEM)	RV535			131	PCIe ×16	587	695	12:5:4:4	7044	2348	733	2348	256	22.2			44			OEM
Radeon X1700 SE	November 30, 2007	RV560			230		500	500	24:8:8:8	12000	4000	1000	4000	512	16.0			50			$
Radeon X1800 CrossFire Edition	December 20, 2005	R520	90	321	288		600	700	16:8:16:16	9600	9600	900	9600	512	46.08		256	113			$
Radeon X1800 GTO	March 9, 2006						500	495	12:8:12:8	6000	6000	1000	6000	256 512	32.0			48			$249
Radeon X1800 XL	October 5, 2005							500	16:8:16:16	8000	8000	1000	8000	256				70			$449
Radeon X1800 XT							625	750		10000	10000	1250	10000	256 512	48.0			113			$499 (256MB) $549 (512 MB)
Radeon X1900 CrossFire Edition	January 24, 2006	R580		384	352		625	725	48:8:16:16	30000				512	46.4			100			$599
Radeon X1900 GT	May 5, 2006						575	600	36:8:12:12	20700	6900	1150	6900	256	38.4			75			$
Radeon X1900 GT Rev. 2	September 7, 2006						512			18432	6144	1024	6144		42.64
Radeon X1900 XT	January 24, 2006						625	725	48:8:16:16	30000	10000	1250	10000	256 512	46.4			100			$549
Radeon X1900 XTX		R580					650	775		31200	10400	1300	10400	512	49.6			135			$649
Radeon X1950 CrossFire Edition	August 23, 2006	R580+	80					1000		31200	10400	1300	10400		64	GDDR4					$449
Radeon X1950 GT	January 29, 2007 (PCIe) February 10, 2007 (AGP)	RV570		330	230	AGP 8x PCIe x16	500	600	36:8:12:12	18000	6000	1000	6000	256 512	38.4	GDDR3		57			$140
Radeon X1950 PRO	October 17, 2006 (PCIe) October 25, 2006 (AGP)						575	690		20700	6900	1150	6900		44.16			66			$199
Radeon X1950 XT	October 17, 2006 (PCIe) February 18, 2007 (AGP)	R580+		384	352	AGP 8x PCIe 1.0 x16	625	700 (AGP) 900 (PCIe)	48:8:16:16	30000	10000	1250	10000		44.8 (AGP) 57.6 (PCIe)			96			$
Radeon X1950 XTX	October 17, 2006					PCIe 1.0 ×16	650	1000		31200	10400	1300	10400	512	64	GDDR4		125			$449
Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Core (MHz)	Memory (MHz)	Core config	MOperations/s	MPixels/s	MVertices/s	MTexels/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Max.	Direct3D	OpenGL	Release price (USD)
							Clock rate			Fillrate				Memory				TDP (Watts)	API support (version)

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units

Radeon HD 2000 series

Main articles: Radeon HD 2000 series and TeraScale 1

Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config	Fillrate		Memory				Processing power (GFLOPS)		TDP (Watts)	Crossfire support	API support (version)			Release price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (Bit)	Single precision	Double precision	Max.		Direct3D	OpenGL	OpenCL
Radeon HD 2350	June 28, 2007	RV610	65	180	85	PCIe 1.0 ×16	525	400	40:4:4	2.10	2.10	64 onboard + up to 256 system	3.20	DDR2	32	42.0	—	20	No	10.0	3.3	APP Stream Only	?
Radeon HD 2400 PRO						PCIe 1.0 ×16 AGP PCI						128 256 512	6.40		64								$50–55
Radeon HD 2400 XT						PCIe 1.0 ×16	650	500 700		2.60	2.60	256	8.0 11.2	DDR2 GDDR3		52.0		25					$75–85
Radeon HD 2600 PRO		RV630		390	153	PCIe 1.0 ×16 AGP	600		120:8:4	2.40	4.80	256 512	16.0 22.4		128	144.0		35					$89–99
Radeon HD 2600 XT							800	800 1100		3.20	6.40		25.6 35.2	GDDR3 GDDR4		192.0		45 50	4-way CrossFire				$119 (GDDR3) $149 (GDDR4)
Radeon HD 2900 GT	November 6, 2007	R600 GT	80	720	420	PCIe 1.0 ×16	601	800	240:12:12	7.21	7.21		51.2	GDDR3	256	288.5		150					$200
Radeon HD 2900 PRO	September 25, 2007	R600 PRO					600	800 925	320:16:16	9.6	9.6	512 1024	51.2 102.4 118.4	GDDR3 GDDR4	256 512	384.0		200					$250 (GDDR3) $300 (GDDR4)
Radeon HD 2900 XT	May 14, 2007	R600 XT					743	828 1000		11.9	11.9		105.6 128.0	GDDR3 GDDR4	512	475.5		215					$399

Radeon HD 3000 series

Main article: Radeon HD 3000 series

Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config	Fillrate		Memory				Processing power (GFLOPS)		TDP (Watts)	Crossfire Support	API support (version)			Release price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (Bit)	Single precision	Double precision	Max.		Direct3D	OpenGL	OpenCL, ATI Stream
Radeon HD 3410	May 7, 2009	RV610	65	180	85	PCIe 1.0 ×16	519	396	40:4:4	2.08	2.08	256	6.34	DDR2	64	41.52	—	20	No	10.0	3.3	No, Yes	?
Radeon HD 3450	January 23, 2008	RV620 LE	55	181	67	PCIe 2.0 ×16 PCI AGP 8×	600	500		2.40	2.40	256 512	8.00			48.0		25		10.1
Radeon HD 3470		RV620 PRO				PCIe 2.0 ×16	800	950		3.20	3.20		15.2	DDR2 GDDR3		64.0		30
Radeon HD 3550	August 4, 2008						594	396		2.38	2.38	512	6.34	DDR2		47.52
Radeon HD 3570	July 5, 2010						796	495		3.18	3.18		7.92			63.68
Radeon HD 3610	September 24, 2009	RV630 PRO	65	390	153	PCIe 1.0 ×16	594	396	120:8:4	2.38	4.75	512 1024	12.7		128	142.6		35
Radeon HD 3650	January 23, 2008	RV635 PRO	55	378		PCIe 2.0 ×16 AGP 8×	725	405 800		2.90	5.80	256 512 1024	13.0 25.6	DDR2 GDDR3 GDDR4		174.0		65	2-way CrossFire
Radeon HD 3730	October 5, 2008				135	PCIe 2.0 ×16	722	405		2.89	5.78	512 1024	13.0	DDR2		173.3			No
Radeon HD 3750							796	693		3.18	6.37	512	22.2	GDDR3		191.0			2-way CrossFire
Radeon HD 3830	April 1, 2008	RV670 PRO		666	192		668	828	320:16:16	10.7	10.7	256	26.5			427.5	85.4	75					$129
Radeon HD 3850	November 19, 2007					PCIe 2.0 x16 AGP 8x		830 900				256 512 1024	53.1 57.6	GDDR3 GDDR4	256		85.4		4-way CrossFire				$179
Radeon HD 3870		RV670 XT					777	900 1126		12.4	12.4	512 1024	57.6 72.1			497.3	99.2	106					$219
Radeon HD 3850 X2	April 4, 2008	RV670 PRO		666×2	192×2	PCIe 2.0 ×16	668	828	320:16:16×2	10.7×2	10.7×2	512×2	53.0×2	GDDR3	256×2	428.2×2	85.6×2	140	2-way CrossFire				$349
Radeon HD 3870 X2	January 28, 2008	R680					825	901 1125		13.2×2	13.2×2		57.6×2 72.1×2	GDDR3 GDDR4		528.0×2	105.6×2	165					$449

IGP (HD 3000)

Main article: AMD 700 chipset series

• All Radeon HD 3000 IGP models include Direct3D 10.0 and OpenGL 3.3

Model	Launch	Code name	Graphics core	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Core clock2 (MHz)	Core config1	Fillrate			Memory3					Processing power (GFLOPS)	Features / Notes
										Pixel (GP/s)	Texture (GT/s)	FP32 (GP/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Effective clock (MHz)	Bus width (Bit)
Radeon 3000 Graphics (760G Chipset)	2009	RS780L[36]	RV610	55	205	~73 (~9 × 8.05)	HT 3.0	350	40:4:4	1.4	1.4	0.7	Up to 512 system	20.8 (system)	HT (system)	—	—	28	AVIVO
Radeon 3100 Graphics (780V Chipset)	2008 Jan 23 (China) Mar 4 (worldwide)	RS780C
Radeon HD 3200 Graphics (780G Chipset)		RS780						500		2	2	1	Up to 512 system + optional 128 sideport	20.8 (system) + 2.6 (sideport)	HT (system) + DDR2-1066 DDR3-1333 (sideport)	1333 (sideport)	16 (sideport)	40	UVD+, 8× AA (wide-tent CFAA)
Radeon HD 3300 Graphics (790GX Chipset)	Jul 2008	RS780D						700		2.8	2.8	1.4	Up to 512 system + 128 sideport		HT (system) + DDR3-1333 (sideport)			56	UVD+, PowerPlay

¹ Unified shaders : Texture mapping units : Render output units
² The clock frequencies may vary in different usage scenarios, as AMD PowerPlay technology is implemented. The clock frequencies listed here refer to the officially announced clock specifications.
³ The sideport is a dedicated memory bus. It is preferably used for a frame buffer.

All-in-Wonder series

Main article: All-in-Wonder

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate			Memory				Performance (GFLOPS)	TDP (Watts)	API (version)
								MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)			Direct3D	OpenGL
All-in-Wonder 128	January 25, 1999	Rage 4	250	AGP PCI	90	90	2:0:2:2	?	?	?	16	1.44	SDR	128	?	5	6	1.2
All-in-Wonder VE	December 2, 2002	RV100	180	PCI	183	183	1:0:3:1	183	549	0	64	2.9	DDR	64	?	10	7.0	1.3
All-in-Wonder Radeon	July 31, 2000	R100		AGP 4×	166	166	2:1:6:2	332	996	41.5	32	5.312		128	?	13
All-in-Wonder 7500	January 22, 2002	RV200	150		260	180		520	1560	65	64	5.760			?	?
All-in-Wonder 8500	April 4, 2002	R200			260	275	4:2:8:4	1100	2200	137.5	128	8.8			?	31	8.1	1.4
All-in-Wonder 8500 DV	August 30, 2001				230	190		920	1840	115	64	6.08			?
All-in-Wonder 9000 Pro	March 31, 2003	RV250		AGP 8x	275	225	4:1:4:4	1110	1110	68.75	64, 128	7.2			?	?
All-in-Wonder 9200	January 26, 2004				250	200		1000	1000	62.5	128	6.4			?	?
All-in-Wonder 9200 SE	N/A					166						2.656		64	?	?
All-in-Wonder 9600	January 26, 2004	RV350	130		325	400	4:2:4:4	1300	1300	162.5		6.4		128	?	17	9.0	2.0
All-in-Wonder 9600 Pro	August 5, 2003				400	650		1600	1600	200		10.4			?	19
All-in-Wonder 9600 XT	January 26, 2004				525			2100	2100	262.5					?	20
All-in-Wonder 9700 Pro	December 30, 2002	R300	150		325	620	8:4:8:8	2600	2600	325		19.84		256	?	50
All-in-Wonder 9800 Pro	April 7, 2003	R350			380	680		3040	3040	380		21.76			?	52
All-in-Wonder 9800 SE	November 1, 2003						4:4:4:8		1520			10.88		128	?	39
All-in-Wonder X600 Pro	September 21, 2004	RV370	110		400	600	4:2:4:4	1600	1600	200	AGP 128, PCIe 256	9.6			?	30
All-in-Wonder X800 GT	August 8, 2005	R430		PCIe ×16	490	980	8:6:8:16	6400	3200	600	128	31.36	GDDR3	256	?	35	9.0b
All-in-Wonder X800 XL	July 5, 2005			PCIe ×16 AGP 8×	400		16:6:16:16		6400		256				?	57
All-in-Wonder X800 XT	September 9, 2004	R420	130	AGP 8×	500	1000		8000	8000	750		32			?	81
All-in-Wonder 2006	December 22, 2005	RV515	90	PCIe ×16	450	800	4:2:4:4	1800	1800	225		12.8	DDR2	128	?	23	9.0c
All-in-Wonder X1800 XL	November 21, 2005	R520			500	1000	16:8:16:16	8000	8000	1000		32	GDDR3	256	?	78
All-in-Wonder X1900	January 24, 2006	R580				960	48:8:16:16					30.72			?	91
All-in-Wonder HD 3650	June 28, 2008	RV635	55		725	1200	120:8:4	2900	5800	N/A	512	19.2	DDR2	128	174.0	26	10.1	3.3

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units

Radeon HD 4000 series

Main articles: Radeon HD 4000 series and TeraScale 1

Model4	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing power (GFLOPS)		TDP3 (Watts)		Crossfire support	API support (version)			Release price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Idle	Max.		Direct3D	OpenGL	OpenCL
Radeon HD 4350	September 30, 2008	RV710	55	242	73	PCIe 2.0 ×16 PCIe 2.0 ×1 AGP 8×	600	400 650	80:8:4	2.40	4.80	256 512 1024	6.40 10.4	DDR2 DDR3	64	92.0	No		20	No	10.1	3.3	1.0	?
Radeon HD 4550	September 30, 2008					PCIe 2.0 ×16	600	655 800					10.5 12.8			96.0	No		25
Radeon HD 4570	November 25, 2008			242			650	500		2.60	5.20	1024	8.00	DDR2		104.0	No
Radeon HD 4580	November 20, 2011	RV635 PRO		378	135		796	693	120:8:4	3.18	6.37	512	22.2	GDDR3	128	191.0	No		65
Radeon HD 4650	September 10, 2008	RV730 PRO		514	146	PCIe 2.0 ×16 AGP 8×	600 650	400 – 500 500 700	320:32:8	4.80 5.20	19.2 20.8	256 512 1024	12.8 - 16.0 16.0 22.4	DDR2 GDDR3 GDDR4	64 128	384.0 416.0	No		48	2-way Crossfire
Radeon HD 4670	September 10, 2008	RV730 XT				PCIe 2.0 ×16 AGP 8×	750	400 – 500 900 1000	320:32:8	6.00	24.0	512 1024	12.8 – 16.0 28.8 32.0	DDR2 GDDR3 GDDR4	128	480.0	No		59					$79
Radeon HD 4730	June 8, 2009	RV770 CE		956	256	PCIe 2.0 ×16	700 750	900	640:32:8	5.60 6.00	22.4 24.0	512	57.6	GDDR5		896.0 960.0	179.2 192.0		110					?
Radeon HD 4750	September 9, 2009	RV740	40	826	137		730	800	640:32:16	11.7	23.4		51.2			934.4			80
Radeon HD 4770	April 28, 2009						750	800		12.0	24.0		51.2			960.0	192.0							$109
Radeon HD 4810	May 28, 2009	RV770 CE	55	956	256		625 750	900	640:32:8	5.00 6.00	20.0 24.0		57.6			800.0 960.0	160.0 192.0		95					?
Radeon HD 4830	October 21, 2008	RV770 LE					575	900	640:32:16	9.20	18.4	512 1024	57.6	GDDR3 GDDR4	256	736.0	147.2							$130
Radeon HD 4850	June 25, 2008	RV770 PRO					625	993	800:40:16	10.0	25.0	512 1024 2048	63.55	GDDR3 GDDR4 GDDR5		1000	200.0		110	4-way Crossfire				$199
Radeon HD 4860	September 9, 2009	RV790 GT		959	282		700	750	640:32:16	11.2	22.4	512 1024	96	GDDR5		896.0	179.2		130					?
Radeon HD 4870	June 25, 2008	RV770 XT		956	256		750	900	800:40:16	12.0	30.0	512 1024 2048	115.2			1200	240.0		150					$299
Radeon HD 4890	April 2, 2009	RV790 XT		959	282		850	975		13.6	34.0	1024 2048	124.8	GDDR5		1360	272.0		190					$249
Radeon HD 4850 X2	November 7, 2008	R700 (2xRV770 PRO)		956×2	256×2		625	995	800:40:16×2	10.0×2	25.0×2	512×2 1024×2	63.7×2	GDDR3	256×2	2000	400.0		250	2-way Crossfire				$339
Radeon HD 4870 X2	August 12, 2008	R700 (2xRV770 XT)					750	900		12×2	30×2	1024×2	115.2×2	GDDR5		2400	480.0		286					$449
Model4	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing power (GFLOPS)		TDP3 (Watts)		Crossfire support	API support (version)			Release price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Idle	Max.		Direct3D	OpenGL	OpenCL

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ The TDP is reference design TDP values from AMD. Different non-reference board designs from vendors may lead to slight variations in actual TDP.
⁴ All models feature UVD2 and PowerPlay.

IGP (HD 4000)

Main articles: AMD 700 chipset series and TeraScale 1

• All Radeon HD 4000 IGP models include Direct3D 10.1 and OpenGL 2.0^[37]

Model	Launch	Code name	Graphics core	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Core		Fillrate			Memory3					Processing power (GFLOPS)	Features / Notes
								Config1	Clock2 (MHz)	Pixel (GP/s)	Texture (GT/s)	FP32 (GP/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Effective clock (MHz)	Bus width (Bit)
Radeon HD 4200 Graphics (785G Chipset)	Aug 2009	RS880	RV620	55	>205	~73 (~9 × 8.05)	HT 3.0	40:4:4	500	2	2	1	Up to 512 system + optional 128 sideport	20.8 (system) + 2.6 (sideport)	HT (system) + DDR2-1066 DDR3-1333 (sideport)	1333 (sideport)	16 (sideport)	40	UVD2
Radeon HD 4250 Graphics (880G Chipset)	Mar 2010	RS880							560	2.24	2.24	1.12			HT (system) + DDR3-1333 (sideport)			44.8
Radeon HD 4290 Graphics (890GX Chipset)		RS880D							700	2.8	2.8	1.4	Up to 512 system + 128 sideport					56

¹ Unified shaders : Texture mapping units : Render output units
² The clock frequencies may vary in different usage scenarios, as ATI PowerPlay technology is implemented. The clock frequencies listed here refer to the officially announced clock specifications.
³ The sideport is a dedicated memory bus. It preferably used for frame buffer.

Radeon HD 5000 series

Main articles: Radeon HD 5000 series and TeraScale 2

• The HD5000 series is the last series of AMD GPUs which supports two analog CRT-monitors with a single graphics card (i.e. with two RAM-DACs).
• AMD Eyefinity introduced.

Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config[a]	Fillrate		Memory				Processing power (GFLOPS)		TDP (Watts)[b]		CrossFire support	API support (version)			Release price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (Bit)	Single precision	Double precision	Idle	Max.		Direct3D	OpenGL	OpenCL
Radeon HD 5450	Feb 4, 2010	Cedar	40	292	59	PCIe 2.1 x16 PCI PCIe 2.1 x1	650 650 650	400 800 800	80:8:4	2.6	5.2	512 1024 2048	6.4 12.8	DDR2 DDR3	64	104	—	6.4	19.1	No	11.3 (11 0)	4.5	1.2	~50
Radeon HD 5550	Feb 9, 2010	Redwood LE		627	104	PCIe 2.1 x16	550 550 550		320:16:8	4.4	8.8		12.8 25.6 51.2	DDR2 GDDR3 GDDR5	128	352		10	39					~70
Radeon HD 5570		Redwood PRO					650 650	400 900	400:20:8	5.2	13.0		12.8 28.8 57.6			520								80
Radeon HD 5610	May 14, 2011						650	500				1024	16.0	GDDR3				?						?
Radeon HD 5670	Jan 14, 2010	Redwood XT					775 775	800 1000		6.2	15.5	512 1024 2048	25.6 64.0	GDDR3 GDDR5		620		15	64	4-way CrossFire				99
Radeon HD 5750	Oct 13, 2009	Juniper PRO		1040	170		700 700	1150 1150	720:36:16	11.2	25.2	512 1024	73.6	GDDR5		1008		16	86					129
Radeon HD 5770		Juniper XT					850 850	1200 1200	800:40:16	13.6	34.0		76.8			1360		18	108					159
Radeon HD 5830	Feb 25, 2010	Cypress LE		2154	334		800	1000	1120:56:16	12.8	44.8	1024	128.0		256	1792	358.4	25	175					239
Radeon HD 5850	Sep 30, 2009	Cypress PRO					725 725	1000 1000	1440:72:32	23.2	52.2	1024 2048				2088	417.6	27	151					259
Radeon HD 5870	Sep 23, 2009	Cypress XT					850 850	1200 1200	1600:80:32	27.2	68.0		153.6			2720	544		188 228					379
Radeon HD 5870 Eyefinity Edition[c][38]	Mar 11, 2010						850	1200				2048							228					479
Radeon HD 5970	Nov 18, 2009	Hemlock		2154×2	334×2		725 725	1000 1000	1600:80:32×2	46.4	116.0	1024×2 2048×2	128×2		256×2	4640	928	51	294	2-way CrossFire				599

• view
• talk
• edit

1. Unified shaders : Texture mapping units : Render output units
2. The TDP is reference design TDP values from AMD. Different non-reference board designs from vendors may lead to slight variations in actual TDP.
3. All chips feature AMD Eyefinity, but the Radeon HD 5870 Eyefinity Edition card also have six mini DisplayPort outputs, all of which can be simultaneously active.

Radeon HD 6000 series

Main articles: Radeon HD 6000 series and TeraScale 3 (VLIW4)

• The Radeon HD 6000 series has a new tesselation engine which is said to double the performance when working with tesselation compared to the previous HD 5000 series.

Model (Codename)	Release Date & Price	Architecture & Fab	Transistors & Die Size	Core		Fillrate[a][b]		Processing power[c] (GFLOPS)		Memory[d]				TDP (Watts)		Bus interface
				Config[e]	Clock (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MB)	Bus type & width	Clock (MHz)	Bandwidth (GB/s)	Idle	Max
Radeon HD 6350 (Cedar)	April 7, 2011 $23 USD	TeraScale 2 40 nm	292×106 59 mm2	80:8:4	650	5.2	2.6	104	—	512	DDR3 64-bit	800	12.8	6.4	19.1	PCIe 2.1 ×16
Radeon HD 6450 (Caicos)	February 7, 2011 OEM		370×106 67 mm2	160:8:4	625 750	5.0 6.0	2.5 3.0	200 240	—	512	DDR3 64-bit	533 800	8.5 12.8	9	18 27
Radeon HD 6450 (Caicos)	April 7, 2011 $55 USD			160:8:4	625 750	5.0 6.0	2.5 3.0	200 240	—	512 1024 2048	DDR3 64-bit	800 900	12.8 14.4	9	18 27
Radeon HD 6570 (Turks Pro)	February 7, 2011 OEM		716×106 118 mm2	480:24:8	650	15.6	5.2	624	—	1024	DDR3 128-bit	900	28.8	10	44
Radeon HD 6570 (Turks Pro)	April 19, 2011 $79 USD			480:24:8	650	15.6	5.2	624	—	2048 4096	DDR3 GDDR5 128-bit	667 1000	21.3 64	11	60
Radeon HD 6670 (Turks XT)	April 19, 2011 $99 USD			480:24:8	800	19.2	6.4	768	—	512 1024 2048		800 1000	25.6 64	12	66
Radeon HD 6750 (Juniper Pro)	January 21, 2011 OEM		1040×106 166 mm2	720:36:16	700	25.2	11.2	1008	—	512 1024	GDDR5 128-bit	1150	73.6	16	86
Radeon HD 6770 (Juniper XT)	April 19, 2011 ?			800:40:16	850	34.0	13.6	1360	—	512 1024		1200 1050	76.8 67.2	18	108
Radeon HD 6790 (Barts LE)	April 4, 2011 $149 USD		1700×106 255 mm2	800:40:16	840	33.6	13.4	1344	—	1024	GDDR5 256-bit	1050	134.4	19	150
Radeon HD 6850 (Barts Pro)	October 22, 2010 $179 USD			960:48:32	775	37.2	24.8	1488	—	1024		1000	128	19	127
Radeon HD 6870 (Barts XT)	October 22, 2010 $239 USD			1120:56:32	900	50.4	28.8	2016	—	1024 2048		1050	134.4	19	151
Radeon HD 6930 (Cayman CE)	December 2011 $180 USD	TeraScale 3 40 nm	2640×106 389 mm2	1280:80:32	750	60.0	24.0	1920	480	1024 2048	GDDR5 256-bit	1200	153.6	18	186
Radeon HD 6950 (Cayman Pro)	December 15, 2010 $259 USD $299 USD			1408:88:32	800	70.4	25.6	2253	563	1024 2048		1250 1250	160	20	200
Radeon HD 6970 (Cayman XT)	December 15, 2010 $369 USD			1536:96:32	880	84.5	28.2	2703	675	2048		1375	176	20	250
Radeon HD 6990 (Antilles XT)	March 8, 2011 $699 USD		2× 2640×106 389 mm2	2× 1536:96:32	830	2× 79.6	2× 26.5	5099	1276.88	2× 2048	GDDR5 256-bit	1250	2× 160	37	375

• view
• talk
• edit

1. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
2. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
3. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
4. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with DDR memory.
5. Unified Shaders : Texture Mapping Units : Render Output Units

IGP (HD 6000)

• All models feature the UNB/MC Bus interface
• All models lack double-precision FP
• With driver Update OpenGL 4.4 available (Last Catalyst 15.12). OpenGL 4.5 available with Crimson Beta (driver version 15.30 or higher).
• All models feature Angle independent anisotropic filtering, UVD3, and AMD Eyefinity capabilities, with up to three outputs.
• All models feature 3D Blu-ray Disc acceleration.
• Embedded GPUs as part of AMD's Lynx platform APUs.

Model	Launch	Codename	Architecture	Fab (nm)	Core Clock rate (MHz)	Config core[a]	Fillrate		Shared Memory			Processing power (GFLOPS)	API compliance (version)				Combined TDP[b]		APU Series
							Pixel (GP/s)	Texture (GT/s)	Bus width (bit)	Bus type	Bandwidth (GB/s)		Direct3D	OpenGL	OpenCL	Vulkan	Idle (W)	Max. (W)
Radeon HD 6370D	November 1, 2011	WinterPark	TeraScale 2	32	443	160:8:4	1.77	3.54	128	DDR3-1600	25.6	142	11.3 (11_0)	4.5	1.2	—	Unknown	65	E2
Radeon HD 6410D	June 20, 2011				443[c]–600		1.77–2.4	3.54–4.8				142–192							A4
Radeon HD 6530D		BeaverCreek			443	320:16:8	3.54	7.08		DDR3-1866	29.9	284						65–100	A6
Radeon HD 6550D					600	400:20:8	4.8	12				480							A8

• view
• talk
• edit

1. Unified Shaders : Texture Mapping Units : Render Output Units
2. TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.
3. A4-3300 series runs the Radeon HD 6410D at a speed of 443 MHz. Remaining A4 series run at 600 MHz.

Radeon HD 7000 series

Main articles: Radeon HD 7000 series, TeraScale 2 (VLIW5), and Graphics Core Next

Model (Codename)	Launch	Architecture Fab	Transistors Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (Watts)		Bus interface	Release Price (USD)
				Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MHz)	Bandwidth (GB/s)	Idle	Max.
Radeon HD 7350 (Cedar)	January 2012	TeraScale 2[g] 40 nm	292×106 59 mm2	80:8:4	400 650	3.2 5.2	1.6 2.6	104	—	256 512	DDR2 DDR3 64-bit	400 800 900	6.4 12.8 14.4	6.4	19.1	PCIe 2.1 ×16	OEM
Radeon HD 7450 (Caicos)	January 2012		370×106 67 mm2	160:8:4	625 750	5.0 6.0	2.5 3.0	200 240	—	512 1024	DDR3 64-bit	533 800	8.5 12.8	9	18	PCIe 2.1 ×16	OEM
Radeon HD 7470 (Caicos)	January 2012			160:8:4	625 775	5.0 6.2	2.5 3.1	200 248	—	512 1024	DDR3 GDDR5 64-bit	800 900	12.8 28.8	9	27	PCIe 2.1 ×16	OEM
Radeon HD 7510 (Turks LE)	February 2013		716×106 118 mm2	320:16:4	650	10.4	2.6	416	—	1024	DDR3 128-bit	667	21.3	Unknown	Unknown	PCIe 2.1 ×16	OEM
Radeon HD 7570 (Turks Pro-L)	January 2012			480:24:8	650	15.6	5.2	624	—	512 1024	DDR3 GDDR5 128-bit	900 1000	28.8 64	10 11	44 60	PCIe 2.1 ×16	OEM
Radeon HD 7670 (Turks XT)	January 2012			480:24:8	800	19.2	6.4	768	—	512 1024	GDDR5 128-bit	1000	64	12	66	PCIe 2.1 ×16	OEM
Radeon HD 7730 (Cape Verde LE)	April 2013	GCN 1st gen 28 nm	1500×106 123 mm2	384:24:8	800	19.2	6.4	614.4	38.4	1024	DDR3 GDDR5 128-bit	1125	25.6 72	10	47	PCIe 3.0 ×16	$60
Radeon HD 7750 (Cape Verde Pro)	February 2012			512:32:16	800 900	25.6 28.8	12.8 14.4	819.2 921.6	51.2 57.6	1024 2048 4096	DDR3 GDDR5 128-bit	800 1125	25.6 72	10	55	PCIe 3.0 ×16	$110
Radeon HD 7770 GHz Edition (Cape Verde XT)	February 2012			640:40:16	1000	40	16	1280	80	1024 2048	GDDR5 128-bit	1125	72	10	80	PCIe 3.0 ×16	$160
Radeon HD 7790 (Bonaire XT)	March 2013	GCN 2nd gen 28 nm	2080×106 160 mm2	896:56:16	1000	56.0	16.0	1792	128	1024 2048	GDDR5 128-bit	1500	96	10	85	PCIe 3.0 ×16	$150
Radeon HD 7850 (Pitcairn Pro)	March 2012	GCN 1st gen 28 nm	2800×106 212 mm2	1024:64:32	860	55.04	27.52	1761.28	110.08	1024 2048	GDDR5 256-bit	1200	153.6	10	130	PCIe 3.0 ×16	$250
Radeon HD 7870 GHz Edition (Pitcairn XT)	March 2012			1280:80:32	1000	80	32	2560	160	2048		1200	153.6	10	175	PCIe 3.0 ×16	$350
Radeon HD 7870 XT (Tahiti LE)	November 2012		4313×106 352 mm2	1536:96:32	925 975	88.8	29.6	2841.6 2995.2	710.4 748.8	2048	GDDR5 256-bit	1500	192.0	15	185	PCIe 3.0 ×16	$270
Radeon HD 7950 (Tahiti Pro)	January 2012			1792:112:32	800	89.6	25.6	2867.2	717	3072	GDDR5 384-bit	1250	240	15	200	PCIe 3.0 ×16	$450
Radeon HD 7950 Boost (Tahiti Pro2)	August 2012			1792:112:32	850 925	103.6	29.6	3046.4 3315.2	761.6 828.8	3072	GDDR5 384-bit	1250	240	15	225	PCIe 3.0 ×16	$330
Radeon HD 7970 (Tahiti XT)	December 2011			2048:128:32	925	118.4	29.6	3788.8	947.2	3072 6144	GDDR5 384-bit	1375	264	15	250	PCIe 3.0 ×16	$550
Radeon HD 7970 GHz Edition (Tahiti XT2)	June 2012			2048:128:32	1000 1050	128.0	32	4096 4300.8	1024 1075	3072 6144	GDDR5 384-bit	1500	288	15	250	PCIe 3.0 ×16	$500
Radeon HD 7990 (New Zealand)	April 2013		2× 4313×106 352 mm2	2× 2048:128:32	950 1000	2× 128	2× 32	7782.4 8192	1945.6 2048	2× 3072	GDDR5 384-bit	1500	2× 288	15	375	PCIe 3.0 ×16	$1000
Model (Codename)	Launch	Architecture Fab	Transistors Die Size	Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MHz)	Bandwidth (GB/s)	Idle	Max.	Bus interface	Release Price (USD)
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (Watts)

• view
• talk
• edit

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with DDR memory.
6. Unified Shaders : Texture Mapping Units : Render Output Units
7. Lacks hardware video encoder

IGP (HD 7000)

• All models feature the UNB/MC Bus interface
• All models do not support double-precision FP
• TeraScale 2 (VLIW5) based APUs feature angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs.
• TeraScale 3 (VLIW4) based APUs feature angle independent anisotropic filtering, UVD3.2, and Eyefinity capabilities, with up to four outputs.

Model	Launch	Code name	Architecture	Fab (nm)	Core Clock (MHz)		Config core[a]	Fillrate		Shared Memory			Processing power (GFLOPS)	API compliance (version)			TDP (W)[b]	APU
					Base	Turbo		Texture (GT/s)	Pixel (GP/s)	Bus width (bit)	Bus type	Bandwidth (GB/s)		Direct3D	OpenGL[c]	OpenCL
Radeon HD 7310[40]	June 6, 2012	Ontario	TeraScale 2[d]	40	500	—	80:8:4	4.00	2.00	64	DDR3-1066	8.53	80	11.3 (11_0)	4.5	1.2	18	E2-1200
Radeon HD 7340[40]					523	680		5.44	2.72		DDR3-1333	10.66	83.6–108.8					E2-1800
Radeon HD 7480D	June 1, 2012	Scrapper	TeraScale 3[d]	32	723	—	128:8:4	11.6	2.9	128	DDR3-1600	25.6	185				65	A4-4000, A4-5300
Radeon HD 7540D					760		192:12:4	Unknown			DDR3-1866	29.9	292					A6-5400K
Radeon HD 7560D		Devastator					256:16:4						389				65–100	A8-5500, A8-5600K
Radeon HD 7660D					760	800	384:24:8	16.2	2.7				584–614					A10-5700 (760 MHz), A10-5800K (800 MHz)

• view
• talk
• edit

1. Unified Shaders : Texture Mapping Units : Render Output Units
2. TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.
3. OpenGL 4.5 possible for Terascale 3 with AMD Radeon Software Crimson Beta (driver 15.30 or higher).^[39]
4. Lacks hardware video encoder

Radeon HD 8000 series

Main articles: Radeon HD 8000 series and Graphics Core Next § first

[ VisualEditor ]

• view
• talk
• edit

Model (Codename)	Launch	Architecture (Fab)	Transistors Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (W)	Bus interface
				Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)	Idle Max
Radeon HD 8350 (Cedar)	January 8, 2013	TeraScale 2[g] (40 nm)	292×106 59 mm2	80:8:4	400–650	3.2 5.2	1.6 2.6	104	—	256 512	DDR2 DDR3 64-bit	400 800	6.4 12.8	6.4 19.1	PCIe 2.1 ×16
Radeon HD 8450 (Caicos)	January 8, 2013		370×106 67 mm2	160:8:4	625	5.0	2.5	200	—	512	DDR3 64-bit	533	8.53	9 18
Radeon HD 8470 (Caicos)	January 8, 2013				750	6.0	3.0	240	—	1024	GDDR5 64-bit	800	25.6	9 35
Radeon HD 8490 (Caicos)	July 23, 2013				875	7.0	3.5	280	—	1024	DDR3L GDDR5 64-bit	800 900	12.8 28.8	9 35
Radeon HD 8570 (Oland)	January 8, 2013	GCN 1st gen (28 nm)	950×106 77 mm2	384:24:8	730	19.2	6.4	560	35	2048	DDR3 GDDR5 128-bit	900 1150	28.8 72	12 66	PCIe 3.0 ×8
Radeon HD 8670 (Oland)	January 8, 2013				1000	24	8	768	48	2048	GDDR5 128-bit	1150	72	16 86
Radeon HD 8730 (Cape Verde LE)	September 5, 2013		1500×106 123 mm2	384:24:8	800	19.2	6.4	614.4	44.8	1024	GDDR5 128-bit	1125	72	10 47	PCIe 3.0 ×16
Radeon HD 8760 (Cape Verde XT)	January 8, 2013			640:40:16	1000	40	16	1280	80	2048	GDDR5 128-bit	1125	72	16 80	PCIe 3.0 ×16
Radeon HD 8770 (Bonaire XT)	September 2, 2013	GCN 2nd gen (28 nm)	2080×106 160 mm2	896:56:16	1000	56.0	16.0	1792	128	2048	GDDR5 128-bit	1500	96	10 85	PCIe 3.0 ×16
Radeon HD 8870 (Pitcairn XT)[41]	January 8, 2013	GCN 1st gen (28 nm)	2800×106 212 mm2	1280:80:32	1000	80	32	2560	160	2048	GDDR5 256-bit	1200	153.6	15 150	PCIe 3.0 ×16
Radeon HD 8950 (Tahiti Pro)	January 8, 2013		4313×106 352 mm2	1792:112:32	850 925	95.2 103.6	27.2 29.6	3046.4 3315.2	761.6 828.8	3072	GDDR5 384-bit	1250	240	15 225	PCIe 3.0 ×16
Radeon HD 8970 (Tahiti XT2)	January 8, 2013			2048:128:32	1000 1050	128.0 134.4	32 33.6	4096 4301	1024 1075	3072	GDDR5 384-bit	1500	288	15 250	PCIe 3.0 ×16
Radeon HD 8990 (Malta)	April 24, 2013		2× 4313×106 2× 352 mm2	2× 2048:128:32	950 1000	2× 128	2× 32	7782 8192	1946 2048	2× 3072	GDDR5 384-bit	1500	2× 288	15 375	PCIe 3.0 ×16
Model (Codename)	Launch	Architecture (Fab)	Transistors Die Size	Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)	Idle Max	Bus interface
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (W)

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as with DDR memory.
6. Unified Shaders : Texture Mapping Units : Render Output Units
7. Lacks hardware video encoder

Radeon 200 series

Main articles: Radeon 200 series and Graphics Core Next § second

Model (codename)	Release Date & Price	Architecture & Fab	Transistors & Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)
Radeon R5 220[42] (Caicos Pro)	December 21, 2013 OEM	Terascale 2[f] 40 nm	370×106 67 mm2	80:8:4	625 650	5	2.5	200	—	1024	DDR3 64-bit	1066	8.53	18 W	PCIe 2.1 ×16
Radeon R5 230[43] (Caicos Pro)	April 3, 2014[44] ?			160:8:4	625	5	2.5	200	—	1024 2048	DDR3 64-bit	1066	8.53	19 W[45]
Radeon R5 235[42] (Caicos XT)	December 21, 2013 OEM			160:8:4	775	6.2	3.1	248	—	1024	DDR3 64-bit	1800	14.4	35 W[46]
Radeon R5 235X[42] (Caicos XT)	December 21, 2013 OEM			160:8:4	875	7.0	3.5	280	—	1024	DDR3 64-bit	1800	14.4	18 W
Radeon R5 240[42] (Oland)	November 1, 2013[47] OEM	GCN 1st gen 28 nm	1040×106 90 mm2	384:24:8	730 780	14.6	5.84	560.6 599	29.2	1024 2048	DDR3 GDDR3 64-bit	1800 2000	14.4 16.0	30 W	PCIe 3.0 ×8
Radeon R7 240[48] (Oland Pro)	August 8, 2013 US $69			320:20:8	730 780	14.6	5.84	467.2 499.2	29.2	2048 4096	DDR3 GDDR5 128-bit	1800 4500	28.8 72	30 W, <45 W (4 GB)[49]
Radeon R7 250[48] (Oland XT)	August 8, 2013 US $89			384:24:8	1000 (1050)	24	8	768 806.4	48	1024 2048	DDR3 GDDR5 128-bit	1800 4600	28.8 73.6	75 W
Radeon R7 250E[50] (Cape Verde Pro)	December 21, 2013 US $109		1500×106 123 mm2	512:32:16	800	25.6	12.8	819.2	51.2	1024 2048	GDDR5 128-bit	4500	72	55 W	PCIe 3.0 ×16
Radeon R7 250X[48] (Cape Verde XT)	February 10, 2014 US $99			640:40:16	1000	40	16	1280	80	1024 2048	GDDR5 128-bit	4500	72	95 W
Radeon R7 260[48] (Bonaire)	December 17, 2013 US $109	GCN 2nd gen 28 nm	2080×106 160 mm2	768:48:16	1000	48	16	1536	96	1024	GDDR5 128-bit	6000	96	95 W
Radeon R7 260X[48] (Bonaire XTX)	August 8, 2013 US $139			896:56:16	1100	61.6	17.6	1971.2	123.2	1024 2048	GDDR5 128-bit	6500	104	115 W
Radeon R7 265[48] (Pitcairn Pro)	February 13, 2014 US $149	GCN 1st gen 28 nm	2800×106 212 mm2	1024:64:32	900 925	57.6	28.8	1843.2	115.2	2048	GDDR5 256-bit	5600	179.2	150 W
Radeon R9 270[51] (Pitcairn XT)	November 13, 2013 US $179			1280:80:32	900 925	72	28.8	2304 2368	144 148	2048	GDDR5 256-bit	5600	179.2	150 W
Radeon R9 270X[51] (Pitcairn XT)	August 8, 2013 US $199			1280:80:32	1000 1050	80	32	2560 2688	160 168	2048 4096	GDDR5 256-bit	5600	179.2	180 W
Radeon R9 280[51] (Tahiti Pro)	March 4, 2014 US $249		4313×106 352 mm2	1792:112:32	827 933	92.6	26.5	2964 3343.9	741 836	3072	GDDR5 384-bit	5000	240	250 W
Radeon R9 280X[51] (Tahiti XTL)[52]	August 8, 2013 US $299			2048:128:32	850 1000	109–128	27.2–32	3481.6 4096	870.4 1024	3072	GDDR5 384-bit	6000	288	250 W
Radeon R9 285[51] (Tonga Pro)	September 2, 2014 US $249	GCN 3rd gen 28 nm	5000×106 359 mm2 [53]	1792:112:32	918	102.8	29.4	3290	206.6[54]	2048	GDDR5 256-bit	5500	176[g]	190 W
Radeon R9 285X (Tonga XT)	Unreleased [56]			2048:128:32	1002	128.3	32.1	4104	256.5	3072	GDDR5 384-bit	5500	264	200 W
Radeon R9 290[51] (Hawaii Pro)	November 5, 2013 US $399	GCN 2nd gen 28 nm	6200×106 438 mm2 [57]	2560:160:64	up to 947[h]	151.52	60.608	4848.6	606.1	4096	GDDR5 512-bit	5000	320	250 W[59]
Radeon R9 290X[51] (Hawaii XT)	October 24, 2013 November 6, 2014[60] US $549			2816:176:64	1000[h]	176	64	5632	704	4096 8192	GDDR5 512-bit	5000	320	250 W[59]
Radeon R9 295X2[51][61] (Vesuvius)	April 8, 2014 US $1499		2× 6200×106 2× 438 mm2	2× 2816:176:64	1018	358.33	130.3	11466.75	1433.34	2× 4096	GDDR5 512-bit	5000	2× 320	500 W
Model (codename)	Release Date & Price	Architecture & Fab	Transistors & Die Size	Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)	TBP	Bus interface
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units
6. Lacks hardware video encoder
7. The R9 285 utilizes loss-less colour compression which can increase effective memory performance (relative to GCN 1^st gen and 2^nd gen cards) in certain situations.^[53][55]
8. Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 °C, respectively.^[58]

Radeon 300 series

Main articles: Radeon 300 series and Graphics Core Next § third

Model (Codename)	Release Date & Price	Architecture (Fab)	Transistors Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TBP (W)	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)
Radeon R5 330 (Oland Pro)	May 2015 OEM	GCN 1st gen (28 nm)	1040×106 90 mm2	320:20:8	Unknown 855	17.1	6.84	547.2	34.2	1024 2048	DDR3 128-bit	1800	28.8	30	PCIe 3.0 x4 x8 ×16
Radeon R5 340 (Oland XT)	May 2015 OEM			384:24:8	Unknown 825	19.8	6.6	633.6	39.6	1024 2048	DDR3 GDDR5 128-bit	1800 4500	28.8 72	75
Radeon R7 340 (Oland XT)	May 2015 OEM			384:24:8	730 780	17.5 18.7	5.8 6.2	560.6 599	32.7 35	1024 2048 4096	DDR3 GDDR5 128-bit	1800 4500	28.8 72	75
Radeon R5 340X[62] (Oland XT)	May 2015 OEM			384:24:8	1050	25.2	8.4	806	50.4	2048	DDR3 64-bit	2000	16	65
Radeon R7 350 (Oland XT)	May 2015 OEM			384:24:8	1000 1050	24 25.2	8 8.4	768 806.4	48 50.4	1024 2048	DDR3 GDDR5 128-bit	1800 4500	28.8 72	75
Radeon R7 350 [63] (Cape Verde XTL)	February 2016 $89 USD		1500×106 123 mm2	512:32:16	925	29.6	14.8	947.2	59.2	2048	GDDR5 128-bit	4500	72	75
Radeon R7 350X[64] (Oland XT)	May 2015 OEM		1040×106 90 mm2	384:24:8	1050	25.2	8.4	806	50.4	4096	DDR3 128-bit	2000	32	30
Radeon R7 360[65][66] (Bonaire Pro)	June 2015 $109 USD	GCN 2nd gen (28 nm)	2080×106 160 mm2	768:48:16	1050	50.4	16.8	1612.8	100.8	2048	GDDR5 128-bit	6500	104	100
Radeon R9 360 (Bonaire Pro)	May 2015 OEM			768:48:16	1000 1050	48 50.4	16 16.8	1536 1612.8	96 100.8	2048	GDDR5 128-bit	6500	104	85
Radeon R7 370[65] (Pitcairn Pro)	June 2015 $149 USD	GCN 1st gen (28 nm)	2800×106 212 mm2	1024:64:32	975	62.4	31.2	1996.8	124.8	2048 4096	GDDR5 256-bit	5600	179.2	110
Radeon R9 370 (Pitcairn Pro)	May 2015 OEM			1024:64:32	950 975	60.8 62.4	30.4 31.2	1945.6 1996.8	121.6 124.8	2048 4096	GDDR5 256-bit	5600	179.2	150
Radeon R9 370X (Pitcairn XT)	August 2015 $179 USD			1280:80:32	1000	80	32	2560	160	2048 4096	GDDR5 256-bit	5600	179.2	185
Radeon R9 380 (Tonga Pro)	May 2015 OEM	GCN 3rd gen (28 nm)	5000×106 359 mm2	1792:112:32	918	102.8	29.4	3290	206.6	4096	GDDR5 256-bit	5500	176	190
Radeon R9 380[67] (Tonga Pro)	June 2015 $199 USD			1792:112:32	970	108.6	31.0	3476.5	217.3	2048 4096	GDDR5 256-bit	5700	182.4[f]	190
Radeon R9 380X[67] (Tonga XT)	November 2015 $229 USD			2048:128:32	970	124.2	31.0	3973.1	248.3	4096	GDDR5 256-bit	5700	182.4	190
Radeon R9 390[67] (Grenada Pro)	June 2015 $329 USD	GCN 2nd gen (28 nm)	6200×106 438 mm2	2560:160:64	1000	160	64	5120	640	8192	GDDR5 512-bit	6000	384	275
Radeon R9 390X[67] (Grenada XT)	June 2015 $429 USD			2816:176:64	1050	184.8	67.2	5913.6	739.2	8192	GDDR5 512-bit	6000	384	275
Radeon R9 Fury[68] (Fiji Pro)	July 2015 $549 USD	GCN 3rd gen (28 nm)	8900×106 596 mm2	3584:224:64	1000	224	64	7168	448	4096	HBM 4096-bit	1000	512	275
Radeon R9 Nano[69] (Fiji XT)	August 2015 $649 USD			4096:256:64	1000	256	64	8192	512					175
Radeon R9 Fury X[67][70] (Fiji XT)	June 2015 $649 USD			4096:256:64	1050	268.8	67.2	8601.6	537.6					275
Radeon Pro Duo[71][72][73][74] (Fiji XT)	April 2016 $1499 USD		2× 8900×106 2× 596 mm2	2× 4096:256:64	1000	512	128	16384	1024	2× 4096	HBM 4096-bit	1000	2× 512	350
Model (Codename)	Release Date & Price	Architecture (Fab)	Transistors Die Size	Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)	TBP (W)	Bus interface
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation. Double precision performance of Hawaii cards is 1/8 of single precision performance, for the other it is 1/16 of single precision performance.
5. Unified Shaders : Texture Mapping Units : Render Output Units
6. The R9 380 utilizes loss-less color compression which can increase effective memory performance (relative to GCN 1^st gen and 2^nd gen cards) in certain situations.^{[citation needed]}

Radeon 400 series

Main articles: Radeon 400 series and Graphics Core Next § fourth

Model (Codename)	Release Date & Price	Architecture & Fab	Transistors & Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (GiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)
Radeon R5 430 (Oland Pro)[75][76]	June 30, 2016 OEM	GCN 1st gen 28 nm	1040×106 90 mm2	384:24:8 6 CU	730 780	17.52 18.72	5.84 6.24	560 599	37.4 40	1 2	DDR3 GDDR5 64-bit	1800 4500	28.8 36	50 W	PCIe 3.0 ×8
Radeon R5 435 (Oland)[75][77]				320:20:8 5 CU	1030	20.6	8.24	659	41.2	2	DDR3 64-bit	2000	16
Radeon R7 430 (Oland Pro)[78][79]				384:24:8 6 CU	730 780	17.52 18.72	5.84 6.24	560 599	37.4 40	1 2 4	DDR3 GDDR5 128-bit	1800 4500	28.8 72
Radeon R7 435 (Oland)[78][80]				320:20:8 5 CU	920	18.4	7.36	589	36.8	2	DDR3 64-bit	2000	16
Radeon R7 450 (Cape Verde Pro)[78][81]			1500×106 123 mm2	512:32:16 8 CU	1050	33.6	16.8	1075	65.2	2 4	GDDR5 128-bit	4500	72	65 W	PCIe 3.0 ×16
Radeon RX 455 (Bonaire Pro)[78][82]		GCN 2nd gen 28 nm	2080×106 160 mm2	768:48:16 12 CU		50.4		1613	100.8	2		6500	104	100 W
Radeon RX 460 (Baffin)[83][84][85][86][87]	August 8, 2016 $109 USD(2 GB) $139 USD(4 GB)	GCN 4th gen GloFo 14LPP[88][f]	3000×106 123 mm2	896:56:16 14 CU	1090 1200	61 67.2	17.4 19.2	1953 2150	122 132	2 4		7000	112	<75 W	PCIe 3.0 ×8
Radeon RX 470D (Ellesmere)[90]	October 21, 2016 CNY ¥1299 (China Only)		5700×106 232 mm2	1792:112:32 28 CU	926 1206	103.7 135.1	29.6 38.6	3319 4322	207 270	4	GDDR5 256-bit		224	120 W	PCIe 3.0 ×16
Radeon RX 470 (Ellesmere Pro)[83][85][86]	August 4, 2016 $179 USD			2048:128:32 32 CU		118.5 154.4		3793 4940	237 309	4 8		6600	211
Radeon RX 480 (Ellesmere XT)[91][92][93][94]	June 29, 2016 $199 USD (4 GB) $239 USD (8 GB)			2304:144:32 36 CU	1120 1266	161.3 182.3	35.8 40.5	5161 5834	323 365			7000 8000	224 256	150 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
6. GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.^[89]

Radeon 500 series

Main articles: Radeon 500 series and Graphics Core Next § fourth

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size	Bus type & width	Clock (MT/s)	Bandwidth (GB/s)
Radeon 520 (Banks)[f][95][96]	Apr 18, 2017 OEM	GCN 1 28 nm	690×106 56mm2	320:20:4 5 CU	1030	20.6	4.1	659.2	41.2	1 GB 2 GB	DDR3 GDDR5 64-bit	2000 4500	16 36	?	PCIe 3.0 ×8
Radeon 530 (Weston)[f][97]		GCN 3 28 nm	? 125 mm2	320:20:8 5 CU	1024	20.480	8.2	655.36	40.96	1 GB 2 GB 4 GB[98]	DDR3 GDDR5 64-bit	1800 4500	14.4 36
				384:24:8 6 CU		24.576		786.432	49.152
Radeon RX 540 (Polaris 12)[99][100]		GCN 4 GloFo 14LPP[g][102]	2.2×109 101 mm2	512:32:16 8 CU	1124 1219	35.968 39.008	17.984 19.504	1150.976 1248.256	71.936 78.016	2 GB 4 GB	GDDR5 128-bit	6000	96		PCIe 3.0 ×8
Radeon RX 550 (Polaris 12)[103][104][105]	Apr 20, 2017 $79 USD				1100 1183	35.2 37.856	17.6 18.928	1126.4 1211.392	70.4 75.712			7000	112	50 W
Radeon RX 550 640SP (Polaris 11)[106]	Apr 20, 2017 $79 USD		3.0×109 123 mm2	640:40:16 10 CU	1019 1071	40.76 42.84	16.304 17.136	1304.32 1370.88	81.52 85.68			6000	96	60 W
Radeon RX 550X (Polaris 12)[107]	Apr 11, 2018 $79 USD		2.2×109 101 mm2	512:32:16 8 CU	1100 1287	35.2 41.184	17.6 20.592	1126.4 1317.888	70.4 82.368			7000	112	50 W
Radeon RX 550X 640SP (Polaris 11)[108]	Apr 11, 2018 OEM		3.0×109 123 mm2	640:40:16 10 CU	1019 1071	40.76 42.84	16.304 17.136	1304.32 1370.88	81.52 85.68			6000	96	60 W
Radeon RX 560D (Polaris 21)[109][110][111]	Jul 4, 2017 OEM and China Only		3.0×109 123 mm2	896:56:16 14 CU	1090 1175	61.0 65.8	17,4 18.8	1953 2106	122,0 131.6					65 W
Radeon RX 560[h] (Polaris 21)[104][109][112]	Jul 4, 2017 $99 USD				1090 1175	61.0 65.8	17.4 18.8	1953 2106	122.0 131.6			7000	112	60-80 W
	Apr 18, 2017 $99 USD			1024:64:16 16 CU	1175 1275	75.2 81.6	18.8 20.4	2406 2611	150.4 163.2
Radeon RX 560 XT (Polaris 10/20)[113]	Mar 13, 2019 China Only		5.7×109 232 mm2	1792:112:32 28 CU	973 1073	109.0 120.2	31.1 34.3	3487 3846	217.3 240.4	4 GB 8 GB	GDDR5 256-bit	6600	211	150 W	PCIe 3.0 ×16
Radeon RX 570 (Polaris 20)[114][104]	Apr 18, 2017 $169 USD			2048:128:32 32 CU	1168 1244	149.5 159.2	37.4 39.8	4784 5095	299.0 318.4			7000	224
Radeon RX 580 2048SP (Polaris 20)[115]	Oct 15, 2018 China Only				1168 1284
Radeon RX 580 (Polaris 20)[116][104]	Apr 18, 2017 $199 USD (4 GB) $229 USD (8 GB)			2304:144:32 36 CU	1257 1340	181.0 193.0	40.2 42.9	5792 6175	362.0 385.9			8000	256	185 W
Radeon RX 590 GME (Polaris 20)[117][118][119]	March 9, 2020 China Only				1257 1380	181.0 198.7	40.2 44.2	5792 6359	362.0 397.4	8 GB				175 W
Radeon RX 590 (Polaris 30)[120]	Nov 15, 2018 $279 USD	GCN 4 Samsung/GloFo 12LP (14LP+)[i]			1469 1545	211.5 222.5	47.0 49.4	6769 7120	423.0 444.9					225 W
Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size	Bus type & width	Clock (MT/s)	Bandwidth (GB/s)	TBP	Bus interface
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)
6. Lacks hardware video encoder and decoder
7. GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.^[101]
8. In October 2017 AMD branded an additional Polaris chip as "RX 560", although it features fewer shader and texture mapping units than the first released RX 560.
9. GlobalFoundries' 12 nm 12LP process is based on Samsung's 14 nm 14LPP process.^[101]

Radeon RX Vega series

Main articles: Radeon RX Vega series and Graphics Core Next § fifth

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX Vega 56 (Vega 10)[121][122][123]	Aug 28, 2017 $399 USD	GCN 5 GloFo 14LPP[f][124][125]	12.5×109 486 mm2	3584:224:64 56 CU	1156 1471	258.9 329.5	73.98 94.14	16,572 21,088	8,286 10,544	517.9 659.0	8	409.6	HBM2 2048-bit	1600	210 W	PCIe 3.0 ×16
Radeon RX Vega 64 (Vega 10)[126][122][123]	Aug 14, 2017 $499 USD			4096:256:64 64 CU	1247 1546	319.2 395.8	79.81 98.94	20,431 25,330	10,215 12,665	638.5 791.6		483.8		1890	295 W
Radeon RX Vega 64 Liquid (Vega 10)[126][122][123]	Aug 14, 2017 $699 USD				1406 1677	359.9 429.3	89.98 107.3	23,036 27,476	11,518 13,738	719.9 858.6					345 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)
6. GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.

Radeon VII series

Main articles: Radeon RX Vega series § Radeon VII branded discrete graphics, and Graphics Core Next § fifth

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon VII (Vega 20)[127][128][129]	Feb 7, 2019 $699 USD	GCN 5 TSMC CLN7FF[130]	13.23×109 331 mm2	3840:240:64 60 CU	1400 1800	336.0 420.0	89.60 112.0	21,504 27,648	10,752 13,824	2,688 3,459	16	1024	HBM2 4096-bit	2000	300 W	PCIe 3.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon RX 5000 series

Main articles: Radeon RX 5000 series and RDNA (microarchitecture)

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 5300 (Navi 14)[131][132]	Aug 28, 2020 OEM	RDNA TSMC N7	6.4×109 158 mm2	1408:88:32 22 CU	1327 1645	116.8 144.8	42.46 52.64	7,474 9,265	3,737 4,632	233.5 289.5	3	168	GDDR6 96-bit	14000	100 W	PCIe 4.0 ×8
Radeon RX 5300 XT (Navi 14)[133][134]	Oct 7, 2019 OEM				1670 1845	146.7 162.4	53.44 59.04	9,405 10,390	4,703 5,196	293.9 324.7	4	112	GDDR5 128-bit	7000
Radeon RX 5500 (Navi 14)[135][136][137]												224	GDDR6 128-bit	14000	150 W
Radeon RX 5500 XT (Navi 14)[138][139][140][141]	Dec 7, 2019 $169 USD (4GB) $199 USD (8GB)				1717 1845	151.1 162.4	54.94 59.04	9,670 10,390	4,835 5,196	302.2 324.7	4 8				130 W
Radeon RX 5600 (Navi 10)[142][143]	Jan 21, 2020 OEM		10.3×109 251 mm2	2048:128:64 32 CU	1375 1560	176.0 199.7	88.00 99.84	11,264 12,780	5,632 6,390	352.0 399.4	6	288	GDDR6 192-bit	12000	150 W	PCIe 4.0 ×16
Radeon RX 5600 XT (Navi 10)[144][145]	Jan 21, 2020 $279 USD			2304:144:64 36 CU		198.0 224.6		12,672 14,377	6,336 7,188	396.0 449.3		288 336		12000 14000	160 W
Radeon RX 5700 (Navi 10)[146][147][148][149][150]	Jul 7, 2019 $349 USD				1465 1725	210.9 248.4	93.73 110.4	13,501 15,900	6,751 7,949	421.9 496.8	8	448	GDDR6 256-bit	14000	180 W
Radeon RX 5700 XT (Navi 10)[151][152][148][149][150]	Jul 7, 2019 $399 USD			2560:160:64 40 CU	1605 1905	256.8 304.8	102.7 121.9	16,435 19,510	8,218 9,754	513.6 609.6					225 W
Radeon RX 5700 XT 50th Anniversary Edition (Navi 10)[153][154][155][150]	Jul 7, 2019 $449 USD				1680 1980	268.8 316.8	107.5 126.7	17,203 20,276	8,602 10,138	537.6 633.6					235 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon RX 6000 series

Main articles: Radeon RX 6000 series and RDNA 2

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Infinity Cache		Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size	Bandwidth (GB/s)	Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 6300 (Navi 24)[156][157][158][f]	Jan 4, 2022[g] OEM	RDNA 2 TSMC N6	5.4×109 107 mm2	768:48:32:12 12 CU	1000 2040	48 97.9	32 65.3	3,072 6,267	1536 3,133	96 195.8	8 MB	104	2 GB	64	GDDR6 32-bit	16000	32 W	PCIe 4.0 ×4
Radeon RX 6400 (Navi 24)[159][160][f]	Jan 19, 2022 $159 USD				1923 2321	92.3 111.4	61.5 74.3	5,907 7,130	2,954 3,565	184.6 222.8	16 MB	208	4 GB	128	GDDR6 64-bit		53 W
Radeon RX 6500 XT (Navi 24)[161][162][163][f]	Jan 19, 2022 $199 USD (4GB) $219 USD (8GB)			1024:64:32:16 16 CU	2310 2815	147.8 180.2	73.9 90.1	9,462 11,530	4,731 5,765	295.6 360.3		232	4 GB 8 GB	144		18000	107 W 113 W
Radeon RX 6600 (Navi 23)[164][165]	Oct 13, 2021 $329 USD	RDNA 2 TSMC N7	11.06×109 237 mm2	1792:112:64:28 28 CU	1626 2491	182.3 279	104.1 159.4	11,658 17,860	5,828 8,928	364.2 558	32 MB	412.9	8 GB	224	GDDR6 128-bit	14000	132 W	PCIe 4.0 ×8
Radeon RX 6600 XT (Navi 23)[166][167][168][169]	Aug 11, 2021 $379 USD			2048:128:64:32 32 CU	1968 2589	251.9 331.4	126 165.7	16,122 21,209	8,061 10,605	503.8 662.8		444.9		256		16000	160 W
Radeon RX 6650 XT (Navi 23)[170][171]	May 10, 2022 $399 USD				2055 2635	263 337.2	131.5 168.6	16,835 21,586	8,417 10,793	526.1 674.6		468.9		280		17500	180 W
Radeon RX 6700 (Navi 22)[172][173][174][175]	Jun 9, 2021		17.2×109 335 mm2	2304:144:64:36 36 CU	1941 2450	279.5 352.8	124.2 156.8	17,888 22,579	8,944 11,290	559 705.6	80 MB	1065	10 GB	320	GDDR6 160-bit	16000	175 W	PCIe 4.0 ×16
Radeon RX 6750 GRE 10GB (Navi 22)[176][177][178]	Oct 18, 2023 $269 USD																170 W
Radeon RX 6700 XT (Navi 22)[179][180][181]	Mar 18, 2021 $479 USD			2560:160:64:40 40 CU	2321 2581	371.4 413	148.5 165.2	23,767 26,429	11,884 13,215	742.7 825.9	96 MB	1278	12 GB	384	GDDR6 192-bit		230 W
Radeon RX 6750 GRE 12GB (Navi 22)[182][183][178]	Oct 18, 2023 $289 USD
Radeon RX 6750 XT (Navi 22)[184][185]	May 10, 2022 $549 USD				2150 2600	344 416	137.6 166.4	22,016 26,624	11,008 13,312	688 832		1326		432		18000	250 W
Radeon RX 6800 (Navi 21)[186][187][188][189]	Nov 18, 2020 $579 USD		26.8×109 520 mm2	3840:240:96:60 60 CU	1700 2105	408 505.2	163.2 202.1	26,112 32,333	13,056 16,166	816 1,010	128 MB	1432.6	16 GB	512	GDDR6 256-bit	16000
Radeon RX 6800 XT (Navi 21)[186][190][188][189]	Nov 18, 2020 $649 USD			4608:288:128:72 72 CU	1825 2250	525.6 648	233.6 288	33,638 41,472	16,819 20,736	1,051 1,296		1664.2					300 W
Radeon RX 6900 XT (Navi 21)[186][191][188][189]	Dec 8, 2020 $999 USD			5120:320:128:80 80 CU	1825 2250	584 720	233.6 288	37,376 46,080	18,688 23,040	1,168 1,440
Radeon RX 6950 XT (Navi 21)[192][193]	May 10, 2022 $1,099 USD				1890 2310	604.8 739.2	241.9 295.7	38,707 47,309	19,354 23,654	1,210 1,478		1793.5		576		18000	335 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)
6. Navi 24 lacks hardware video encoder.
7. Actual release date unknown; RX 6300M release date is listed instead.

Radeon RX 7000 series

Main articles: Radeon RX 7000 series and RDNA 3

Model (Code name)	Release Date & Price	Architecture & fab	Chiplets	Transistors & die size[i]	Core		Fillrate[ii][iii][iv]		Processing power[ii][v] (TFLOPS)			Infinity Cache		Memory				TBP	Bus interface
					Config[vi]	Clock[ii] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half[vii]	Single	Double	Size	Bandwidth (GB/s)	Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 7400 (Navi 33)[194][195]	Aug 10, 2025 OEM	RDNA 3 TSMC N6	Monolithic	13.3×109 204 mm2	1792:112:64:28:56 28 CU	1100			15.77	7.88	0.246	32 MB	362	8 GB	173	GDDR6 128-bit	10800	55 W	PCIe 4.0 ×8
Radeon RX 7600 (Navi 33)[196]	May 25, 2023 $269 USD				2048:128:64:32:64 32 CU	1720 2655	220.2 339.8	110.1 169.9	14.09 21.75	14.09 21.75	0.220 0.340		476.9		288		18000	165 W
Radeon RX 7650 GRE (Navi 33)[197][198][199]	Feb 7, 2025 China Only ¥2,049 RMB ($249 USD)					1720 2695	220.2 345.0	110.1 172.5	14.09 22.08	14.09 22.08	0.220 0.345							170 W
Radeon RX 7600 XT (Navi 33)[200][201]	Jan 24, 2024 $329 USD					1720 2755	220.2 352.6	110.1 176.3	14.09 22.57	14.09 22.57	0.220 0.353			16 GB				190 W
Radeon RX 7700 (Navi 32)[202][203]	Sep 18, 2025 OEM	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 4 × MCD	28.1×109 346 mm2	2560:160:64:40:80 40 CU	1900 2459	304 393.4	121.6 157.4	19.47 25.20	19.47 25.20	0.304 0.394	40 MB	1927		624	GDDR6 256-bit	19500	263 W	PCIe 4.0 ×16
Radeon RX 7700 XT (Navi 32)[204]	Sep 6, 2023 $449 USD		1 × GCD 3 × MCD		3456:216:96:54:108 54 CU	1900 2544	410.4 549.5	182.4 244.2	26.27 35.17	26.27 35.17	0.410 0.550	48 MB	1995	12 GB	432	GDDR6 192-bit	18000	245 W
Radeon RX 7800 XT (Navi 32)[205]	Sep 6, 2023 $499 USD		1 × GCD 4 × MCD		3840:240:96:60:120 60 CU	1800 2430	432 583.2	172.8 233.2	27.64 37.32	27.64 37.32	0.432 0.583	64 MB	2708	16 GB	624	GDDR6 256-bit	19500	263 W
Radeon RX 7900 GRE (Navi 31)[206][207]	Jul 27, 2023 China only, Feb 27, 2024 $549 USD			57.7×109 529 mm2	5120:320:160:80:160 80 CU	1270 2245	406.4 718.4	243.8 431.0	26.01 45.98	26.01 45.98	0.406 0.718		2250		576		18000	260 W
Radeon RX 7900 XT (Navi 31)[208]	Dec 13, 2022 $899 USD		1 × GCD 5 × MCD		5376:336:192:84:168 84 CU	1500 2400	504.0 806.4	288.0 460.8	32.26 51.61	32.26 51.61	0.504 0.806	80 MB	2900	20 GB	800	GDDR6 320-bit	20000	315 W
Radeon RX 7900 XTX (Navi 31)[209]	Dec 13, 2022 $999 USD		1 × GCD 6 × MCD		6144:384:192:96:192 96 CU	1900 2500	729.6 960.0	364.8 480.0	46.69 61.44	46.69 61.44	0.730 0.960	96 MB	3500	24 GB	960	GDDR6 384-bit		355 W

• v
• t
• e

1. Approximate die size of all active dies (one GCD and up to six MCD).^[210]
2. Boost values (if available) are stated below the base value in italic.
3. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
4. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
5. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
6. Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute Units (CU)
7. Officially declared half-precision performance is twice of the one shown here due to being based on different operation (a×b+c×d+e).

Radeon RX 9000 series

Main articles: Radeon RX 9000 series and RDNA 4

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[i][ii][iii]		Processing power					Infinity Cache		Memory				TBP	Bus interface
								TFLOPS[i][iv]			AI TOPS[v]
				Config[vi]	Clock[i] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half[vii]	Single	Double	INT8	INT4	Size	Bandwidth (GB/s)	Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 9060 (Navi 44)[211]	Aug 5, 2025 OEM	RDNA 4 TSMC N4P	29.7 billion 199 mm2	1792:112:64:28:56 28 CU	1700 2990	190.4 334.9	108.8 191.4	24.37 42.84	12.19 21.43	0.190 0.335	97 171	195 343	32 MB		8 GB	288	GDDR6 128-bit	18000	132 W	PCIe 5.0 ×16
Radeon RX 9060 XT (Navi 44)[212][213]	Jun 5, 2025 $299 USD (8 GB) $349 USD (16 GB)			2048:128:64:32:64 32 CU	2530 3130	323.8 400.6	161.9 200.3	41.45 51.28	20.72 25.64	0.323 0.400	166 205	331 410	32 MB		8 GB 16 GB	320		20000	150 W 160 W
Radeon RX 9070 GRE (Navi 48)[214]	May, 2025 ¥4119 RMB		53.9 billion 356.5 mm2	3072:192:96:48:96 48 CU	2200 2790	422.4 535.7	211.2 267.8	54.07 68.57	27.03 34.28	0.422 0.535	216 274	432 548	48 MB		12 GB	432	GDDR6 192-bit	18000	220 W
Radeon RX 9070 (Navi 48)[215]	Mar 6, 2025 $549 USD			3584:224:128:56:112 56 CU	2070 2520	463.6 564.4	265.0 322.6	59.35 72.25	29.67 36.12	0.463 0.564	237 289	475 578	64 MB		16 GB	640	GDDR6 256-bit	20000
Radeon RX 9070 XT (Navi 48)[216]	Mar 6, 2025 $599 USD			4096:256:128:64:128 64 CU	2400 2970	614.4 760.3	307.2 380.2	78.64 97.32	39.32 48.66	0.614 0.760	314 389	629 778							304 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Officially declared performance is twice the one shown here due to the use of sparsity.
6. Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
7. Officially declared half-precision performance is twice of the one shown here due to being based on different operation (a×b+c×d+e).

Mobile GPUs

These GPUs are either integrated into the mainboard or occupy a Mobile PCI Express Module (MXM).

Rage Mobility series

Main article: ATI Rage

Model	Launch	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Hardware T&L	Core config1	Fillrate		Memory				API compliance (version)		Notes
								Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Rage LT (Rage II)	Nov 1996	500	PCI	60	66	No	0:1:1:1	0.06	0.06	4	0.53	EDO, SDR, SGR	64	5	N/A
Rage LT Pro (Rage Pro)	Nov 1997	350	AGP, PCI	75	100			0.075	0.075	8	0.80			6	1.1	Motion compensation
Rage Mobility M/P (Rage Pro)	Nov 1998	250		90	Unknown			0.18	0.18		Unknown	SDR, SGR		Unknown	Unknown	M had 4 MB of integrated SDRAM, P had none. IDCT, motion compensation.
Rage Mobility M1 (Rage Pro)	Feb 1999			90	90						0.72	SDR		6	1.2	M1 had 8 MB of integrated SDRAM, P had none. IDCT, motion compensation.
Rage 128 GL	Aug 1998			103	103		0:2:2:2	0.206	0.206	32	1.65		128
Rage Mobility 128 (Rage 128 Pro)	Oct 1999			105	105			0.21	0.21	16	2.28					IDCT, Motion Compensation
Rage Mobility M3 (AGP 4×) (Rage 128 Pro)											2.28					M3 had 8 MB of integrated SDRAM, IDCT, Motion Compensation.
Rage Mobility M4 (AGP 4×) (Rage 128 Pro)										32	2.28					M4 had 16 MB of integrated SDRAM, IDCT, Motion Compensation.

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon series

Model	Launch	Model number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon 7000	Feb 2001	M6	RV100	180	AGP 4×	144 167	144 183	0:1:3:1	0.167	0.5	8 16 32	1.464 2.928	SDR DDR	32 64	7	1.3
Mobility Radeon 7500	Dec 2001	M7	RV200	150		280	200	1:2:6:2	0.56	1.68	32 64	3.2 6.4	DDR	64 128	7		PowerPlay II, DX7 T&L
Mobility Radeon 9000	Aug 2002	M9	RV250			250		1:4:4:4	1.0	1.0					8.1	1.4	PowerPlay 3.0, Fullstream
Mobility Radeon 9200	Mar 2003	M9+	RV280		AGP 8×	250/250	200/220					3.2/3.52 6.4/7.04
Mobility Radeon 9500	2004?	M11	RV360	130		Unknown	Unknown	2:4:4:4	Unknown	Unknown	64	Unknown			9.0	2.0
Mobility Radeon 9550	2005	M12				210	183		0.84	0.84		2.928 5.856
Mobility Radeon 9600	Mar 2003	M10, M11	RV350			300	300		1.2	1.2	64 128	4.8 9.6
Mobility Radeon 9600 Pro	2004	M10				350	350		1.4	1.4	128	11.2		128
Mobility Radeon 9700	Feb 2004	M11	RV360			450	275		1.8	1.8		8.8
Mobility Radeon 9800	Sep 2004	M18	R420			350	300	4:8:8:8	2.8	2.8	256	19.2		256

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon X300, X600, X700, X800 series

Model	Launch	Model number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon X300	Nov 2005	M22	RV370	110	PCIe ×16	350	250	2:4:4:4	1.4	1.4	128	4	DDR	64	9.0b	2.0	Powerplay 5.0
Mobility Radeon X600	Jun 2004	M24	RV380	130		400			1.6	1.6	64, 128	8		128
Mobility Radeon X700	Mar 2005	M26	RV410	110		400-100 (PowerPlay)	350-200	6:8:8:4	1.4	2.8	Shared-128? 64, 128	11.2	DDR, GDDR3				3DC, dynamic lane count switching
Mobility Radeon X800	Nov 2004	M28	R423	130		400	400	6:12:12:12	4.8	4.8	256	25.6	GDDR3	256			3DC, DLCS, Clock Gating
Mobility Radeon X800 XT	Jun 2005	M28 PRO	R423	130		480	550	6:16:16:16	7.68	7.68		35.2

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon X1000 series

Main article: Radeon X1000 series

Model	Launch	Model number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon X1300	January 19, 2006	M52	RV515	90	PCIe ×16	350	250	2:4:4:4	1.4	1.4	128 + shared	8	DDR DDR2	128	9.0c	2.0
Mobility Radeon X1350	September 18, 2006	M62				470	350		1.88	1.88		11.2	DDR2 GDDR3
Mobility Radeon X1400	January 19, 2006	M54				445	250		1.78	1.78		8	DDR DDR2
Mobility Radeon X1450	September 18, 2006	M64				550	450		2.2	2.2		14.4	DDR2 GDDR3
Mobility Radeon X1600	February 1, 2006	M56	RV530			425 450	375 470	5:12:4:4	1.7 1.8	1.7 1.8	256	12.0 15.04	DDR2 GDDR3
Mobility Radeon X1700		M66	RV535			475	400 550		1.9	1.9		11.2 17.6					strained silicon
Mobility Radeon X1800	March 1, 2006	M58	R520			450	500	8:12:12:12	5.4	5.4		32	GDDR3	256
Mobility Radeon X1800 XT		M58				550	650	8:16:16:16	8.8	8.8		41.6
Mobility Radeon X1900	January 11, 2007	M68	RV570	80		400	470	8:36:12:12	4.8	4.8		30.08					PowerPlay 6.0

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon HD 2000 series

Main article: Radeon HD 2000 series

OpenGL 3.3 is possible with latest drivers for all RV6xx.

Model	Launch	Model number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config	Fillrate		Memory				API compliance (version)		Processing power (GFLOPS)	Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon X2300	March 1, 2007	M64	RV515	90	PCIe ×16	480	400	2:4:4:41	1.92	1.92	128	6.4 12.8	DDR DDR2 GDDR3	64 128	9.0c	2.0	Unknown	renamed product, HyperMemory, no UVD, PowerPlay 6.0
Mobility Radeon X2500	June 1, 2007	M66	RV530			460		5:12:4:41	1.84	1.84	256	12.8		128			Unknown	based on X1600/1700, HM up to 768 Mb, no UVD, PowerPlay 6.0
Mobility Radeon HD 2300	March 1, 2007	M71	RV515			480		2:4:4:41	1.92	1.92	128 256 512	6.4 12.8		64 128			Unknown	same as X2300, but with UVD, PowerPlay 6.0
Mobility Radeon HD 2400	May 14, 2007	M72S	RV610	65		450		40:4:42	1.8	1.8	256+ Hyper Memory	6.4	DDR2	64	10.0	2.0 (3.3)	36	UVD, PowerPlay 7.0
Mobility Radeon HD 2400 XT		M72M				600 600	400 700		2.4	2.4		6.4 11.2	DDR2 GDDR3				48
Mobility Radeon HD 2600		M76M	RV630			500 500	400 600	120:8:42	2.0	4.0		12.8 19.2		128			120
Mobility Radeon HD 2600 XT		M76XT				680	750		2.72	5.44		24	GDDR3				168
Mobility Radeon HD 2700	December 12, 2007	M76				650	700		2.6	5.2	256+ Hyper Memory (total 768)	22.4

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units.
² Unified Shaderss : Texture mapping units : Render output units

Mobility Radeon HD 3000 series

Main article: Radeon HD 3000 series

Model[217]	Launch	Model number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Processing power (GFLOPS)	TDP (Watts)	Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon HD 3100	August 1, 2008	RS780MC	RV620	55	PCIe ×16 1.1	300	800 (system memory)	40:4:4	1.2	1.2	up to 512 from system memory	6.4/12.8	DDR2	64/128	10.1	2.0 (3.3)	24		UVD, PowerPlay 7.0
Mobility Radeon HD 3200	June 4, 2008	RS780MC				500	800 (system memory)		2	2		6.4/12.8					40
Mobility Radeon HD 3410	July 25, 2008	M82-MPE				400	400		1.6	1.6	256, 512	6.4		64			32
Mobility Radeon HD 3430		M82-SE			PCIe ×16 2.0	450	400		1.8	1.8	256	6.4					36
Mobility Radeon HD 3450	January 7, 2008	M82				500	400 700		2	2		6.4 11.2	DDR2 GDDR3				40
Mobility Radeon HD 3470		M82-XT				680	400 800		2.72	2.72		6.4 12.8					54.4
Mobility Radeon HD 3650		M86	RV635			500	500 700	120:8:4	2	4	512 1024	16.0 22.4	DDR2 GDDR3 GDDR4	128		3.3	120
Mobility Radeon HD 3670		M86-XT				680	800		2.72	5.44		25.6				2.0 (3.3)	163.2	30	UVD, PowerPlay 7.0
Mobility Radeon HD 3850	June 4, 2008	M88-L/M88-LP	RV670			580	750	320:16:16	9.28	9.28	512	48.0	GDDR3	256			371.2
Mobility Radeon HD 3870		M88-LXT				660	850		10.56	10.56		54.4					422.4	55
Mobility Radeon HD 3850 X2	June 5, 2008	2× M88-L/M88-LP	R680			580	750	2x [320:16:16]	2× 9.28	2× 9.28	2× 512	2× 48.0		2× 256			2× 371.2
Mobility Radeon HD 3870 X2	September 1, 2008	2× M88-LXT				660	850		2× 10.56	2× 10.56		2× 54.4					2× 422.4	110

¹ Unified Shaders : Texture mapping units : Render output units

Mobility Radeon HD 4000 series

Main article: Radeon HD 4000 series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Processing power (GFLOPS)	Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon HD 4200	September 10, 2009	Unknown	RV620	55	Internal PCIe x16 1.1	500	800 (system memory)	40:4:4	2	2	up to 512 from system memory	6.4/12.8	DDR2 DDR3	64/128	10.1	3.3	40	UVD2, PowerPlay 7.0
Mobility Radeon HD 4225	May 1, 2010	Unknown				380			1.52	1.52							30.4
Mobility Radeon HD 4250		Unknown				500			2	2							40
Mobility Radeon HD 4270		Unknown				590			2.36	2.36							47.2
Mobility Radeon HD 4330	January 9, 2009	M92	RV710		PCIe ×16 2.0	450	600	80:8:4	1.8	3.6	512	9.6	DDR2 DDR3 GDDR3	64			72
Mobility Radeon HD 4530						500	700		2	4		11.2					80
Mobility Radeon HD 4550	January 1, 2010					550			2.2	4.4							80
Mobility Radeon HD 4570	January 9, 2009					680	800		2.72	5.44		12.8					108.8
Mobility Radeon HD 4650		M96	RV730			500 550	600 800	320:32:8	4 4.4	16 17.6	512 1024	19.2 25.6	DDR2 DDR3 GDDR3	128			320 352
Mobility Radeon HD 4670		M96-XT				675	800		5.4	21.6		12.8 25.6					432
Mobility Radeon HD 4830	March 3, 2009[218]	M97	RV740	40		400/600 400/600	800/900 800/900	640:32:16	6.4/9.6 6.4/9.6	12.8/19.2 12.8/19.2		25.6/28.8 25.6/28.8	GDDR3 DDR3				512/768 512/768
Mobility Radeon HD 4850[219]	January 9, 2009	M98	RV770	55		500	850 700	800:40:16	8	20	1024	54.4 89.6	GDDR3 GDDR52	256			800
Mobility Radeon HD 4860	March 3, 2009[218]	M97	RV740	40		650	1000	640:32:16	10.4	20.8		64.0	GDDR52	128			832
Mobility Radeon HD 4870	January 9, 2009	M98-XT	RV770	55		550	888 700	800:40:16	8.8	22	512 1024	56.832 89.6	GDDR3 GDDR52	256			880
Mobility Radeon HD 4870 X2						550	700	2× [800:40:16]	2× 8.8	2× 22	2048	2× 89.6	GDDR52	2× 256			2× 880	UVD2, PowerPlay 7.0 Dual GPU solution

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

Mobility Radeon HD 5000 series

Main article: Radeon HD 5000 series

Model: Mobility Radeon	Launch	Model Number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		Processing power (GFLOPS)	TDP (Watts)
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Mobility Radeon HD 530v[220]	May 5, 2010	M92	RV710	55	PCIe ×16 2.0	500	600	80:8:4	2	4	1024	9.6	DDR2 DDR3 GDDR3	64	10.1	3.3	80	10
Mobility Radeon HD 545v[221]						720	400 800		2.88	5.76	512 1024	6.4 12.8					115.2	15
Mobility Radeon HD 550v[222]		M96	RV730			450	600	320:32:8	3.6	14.4	1024	19.2		128			288	10
Mobility Radeon HD 560v[223]						550	800		4.4	17.6		25.6					352	15
Mobility Radeon HD 565v[224]		M96-XT				675			5.4	21.6		25.6					432	20
Mobility Radeon HD 5145	January 7, 2010	M92	RV710			720	900	80:8:4	2.88	5.76		14.4	DDR3 GDDR3	64			115.2	15
Mobility Radeon HD 5165		M96	RV730			600		320:32:8	4.8	19.2		28.8		128			384	35
Mobility Radeon HD 5430		Park LP	Cedar (RV 810)	40	PCIe ×16 2.1	500 550	800	80:8:4	2.0 2.2	4.0 4.4		12.8		64	11	4.4	80 88	7
Mobility Radeon HD 5450		Park PRO				675			2.7	5.4							108	11
Mobility Radeon HD 5470		Park XT				750			3	6	1024 512	12.8 25.6	DDR3 GDDR3 GDDR5				120	13 15
Mobility Radeon HD 5650		Madison PRO	Redwood (RV 830)			450 650		400:20:8	3.6 5.2	9.0 13.0	1024	25.6	DDR3 GDDR3	128			360 520	15 19
Mobility Radeon HD 5730		Madison LP				650			5.2	13							520	26
Mobility Radeon HD 5750		Madison PRO				550			4.4	11		51.2	GDDR5				440	25
Mobility Radeon HD 5770		Madison XT			PCIe ×16 2.0/2.1	650			5.2	13							520	30
Mobility Radeon HD 5830		Broadway LP	Juniper (RV 840)		PCIe ×16 2.1	500		800:40:16	8	20		25.6	DDR3 GDDR3				800	24
Mobility Radeon HD 5850		Broadway PRO				625 500 625	900 1000	800:40:16	10 8 10	25 20 25	2048 1024	28.8 64 64					1000 800 1000az	31 30 39
Mobility Radeon HD 5870		Broadway XT				700	1000		11.2	28	1024	64	GDDR5				1120	50
Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL	Processing power (GFLOPS)	TDP (Watts)
									Fillrate		Memory				API compliance (version)

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

Radeon HD 6000M series

Main article: Radeon HD 6000 series

Model[225]	Launch	Architecture Fab	Core		Fillrate[a][b]		Processing power[c] (GFLOPS)	Memory				TDP (Watts)	Bus interface
			Config[d]	Clock (MHz)	Pixel (GP/s)	Texture (GT/s)		Size (MiB)	Bus type & width	Clock (MHz)	Bandwidth (GB/s)
Radeon HD 6330M (Robson LP)[226]	November 2010	TeraScale 2 40 nm	80:8:4	500	2.0	4.0	80	1024	DDR3 64-bit	800	12.8	7	PCIe 2.1 x16
Radeon HD 6350M (Robson Pro)[226]	November 2010			500	2.0	4.0	80	1024	DDR3 64-bit	800 900	12.8 14.4	7
Radeon HD 6370M (Robson XT)[226]	November 2010			750	3.0	6.0	120	1024	DDR3 64-bit	900	14.4	11
Radeon HD 6430M (Seymour LP)[227]	January 2011	TeraScale 2 40 nm	160:8:4	480	1.92	3.84	153.6	1024	DDR3 64-bit	800	12.8	Unknown	PCIe 2.1 x16
Radeon HD 6450M (Seymour Pro)[227]	January 2011			600	2.4	4.8	192	1024	DDR3 64-bit	800	12.8	Unknown
Radeon HD 6470M (Seymour XT)[227]	January 2011			700 750	2.8 3.0	5.6 6.0	224 240	1024	DDR3 64-bit	800 800	12.8	Unknown
Radeon HD 6490M (Seymour XT)[227]	January 2011			800	3.2	6.4	256	512	GDDR5 64-bit	800	25.6	Unknown
Radeon HD 6530M (Capilano Pro)[228]	November 2010	TeraScale 2 40 nm	400:20:8	500	4.0	10.0	400	1024	DDR3 128-bit	900	28.8	26	PCIe 2.1 x16
Radeon HD 6550M (Capilano Pro)[228]	November 2010			600	4.8	12.0	480	1024	DDR3 128-bit	900	28.8	26
Radeon HD 6570M (Capilano XT)[228]	November 2010			650	5.2	13.0	520	1024	DDR3 64-bit GDDR5 128-bit	900	28.8 57.6	30
Radeon HD 6630M (Whistler LP)[229]	January 2011	TeraScale 2 40 nm	480:24:8	485	3.88	11.64	465.6	256 (Mac) 1024	GDDR5 128-bit (Mac) DDR3 128-bit	800	51.2 (Mac) 25.6	Unknown	PCIe 2.1 x16
Radeon HD 6650M (Whistler Pro)[229]	January 2011			600	4.8	14.4	576	1024	DDR3 128-bit	900	28.8	Unknown
Radeon HD 6730M (Whistler XT)[229]	January 2011			725	5.8	17.4	696	1024	DDR3 128-bit	800	25.6	Unknown
Radeon HD 6750M (Whistler Pro)[229]	January 2011			600	4.8	14.4	576	256 512 1024	GDDR5 128-bit	800 900	51.2 57.6	Unknown
Radeon HD 6770M (Whistler XT)[229]	January 2011			725	5.8	17.4	696	1024	GDDR5 128-bit	900	57.6	Unknown
Radeon HD 6830M (Granville Pro)[230]	January 2011	TeraScale 2 40 nm	800:40:16	575	9.2	23.0	920	2048	DDR3 128-bit	800	25.6	39	PCIe 2.1 x16
Radeon HD 6850M (Granville XT)[230]	January 2011			675	10.8	27.0	1080	2048	DDR3 128-bit	800	25.6	50
Radeon HD 6850M (Granville Pro)[230]	January 2011			575	9.2	23.0	920	1024	GDDR5 128-bit	800	57.6	39
Radeon HD 6870M (Granville XT)[230]	January 2011			675	10.8	27	1080	1024	GDDR5 128-bit	1000	64	50
Radeon HD 6950M (Blackcomb Pro)[231]	January 2011	TeraScale 2 40 nm	960:48:32	580	18.56	27.84	1113.6	2048	GDDR5 256-bit	900	115.2	50	PCIe 2.1 x16
Radeon HD 6970M (Blackcomb XT)[231]	January 2011			680	21.76	32.64	1305.6	2048	GDDR5 256-bit	900	115.2	75
Radeon HD 6990M (Blackcomb XTX)[232]	July 2011	TeraScale 2 40 nm	1120:56:32	715	22.88	40.04	1601.6	2048	GDDR5 256-bit	900	115.2	75	PCIe 2.1 x16

• v
• t
• e

1. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the core clock speed.
2. Pixel fillrate is calculated as the number of Render Output Units multiplied by the core clock speed.
3. Single Precision performance is calculated from the core clock speed based on a FMA operation.
4. Unified Shaders : Texture Mapping Units : Render Output Units

IGP (HD 6000)

• All models feature the UNB/MC Bus interface
• All models lack double-precision FP
• All models feature Angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs.

Model	Released	Code name	Architecture	Fab (nm)	Core clock rate (MHz)	Config core[a]	Fillrate		Shared memory			Processing power (GFLOPS)	API compliance (version)				Combined TDP[b]		APU
							Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)		Direct3D	OpenGL	OpenCL	Vulkan	Idle (W)	Max. (W)
Radeon HD 6250[233]	November 9, 2010[234]	Wrestler[235]	TeraScale 2	40	280–400	80:8:4:2	1.12–1.6	2.24–3.2	8.525	DDR3-1066	64	44.8–64	11.3 (11_0)	4.5	1.2	—	Unknown	9	C-30, C-50, Z-60
Radeon HD 6290	January 7, 2011	Ontario			276–400														C-60
Radeon HD 6310[233]	November 9, 2010[234]	Wrestler[235]			492		2.0	4.0				80						18	E-240, E-300, E-350
Radeon HD 6320	August 15, 2011				508–600		2.032–2.4	4.064–4.8	10.6	DDR3-1333		82–97							E-450

• v
• t
• e

1. Unified Shaders : Texture Mapping Units : Render Output Units : Compute units
2. TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

IGP (HD 6000G)

• All models include Direct3D 11, OpenGL 4.4 and OpenCL 1.2
• All models feature the UNB/MC Bus interface
• All models lack double-precision FP
• All models feature angle independent anisotropic filtering, UVD3 and Eyefinity capabilities, with up to three outputs.
• All models feature VLIW5

Model	Released	Code name	Fab (nm)	Core clock (MHz)	Core config1	Fillrate		Shared Memory			Processing power (GFLOPS)	Max. combined TDP2 (Watts)	APU
						Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon HD 6380G	June 14, 2011	WinterPark	32	400	160:8:4:2	1.6	3.2	17.06	DDR3-1333	128	128	35	E2-3000M
Radeon HD 6480G		BeaverCreek		444	240:12:4:3	1.77	3.55				213.1	35 - 45	A4-3300M A4-3310MX
Radeon HD 6520G				400	320:16:8:4	3.2	6.4				256		A6-3400M A6-3410MX A6-3420M
Radeon HD 6620G				444	400:20:8:5	3.55	8.88	25.6	DDR3-1600		355.2		A8-3500M A8-3510MX A8-3530MX

¹ Unified shaders : Texture mapping units : Render output units : Compute units
² TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

Radeon HD 7000M series

Main article: Radeon HD 7000 series

A Radeon HD 7970M GPU on a Mobile PCI Express Module

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate		Processing power (GFLOPS)	Memory				Bus interface	TDP (W)
			Config[a]	Clock (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (GiB)	Bus type & width (bit)[b]	Memory (MHz)	Bandwidth (GB/s)
Radeon HD 7430M (Seymour Pro)	January 2012	TeraScale 2[c] (40 nm)	160:8:4:2	600	4.8	2.4	192	1	DDR3 64-bit	900	14.4	PCIe 2.1 ×16	7
Radeon HD 7450M (Seymour Pro)				700 700	5.6	2.8	224	1	DDR3 GDDR5 64-bit	900 800	14.4 25.6		7
Radeon HD 7470M (Seymour XT)				750 800	6 6.4	3.0 3.2	240 256	1	DDR3 GDDR5 64-bit	900 800	14.4 25.6		7~9
Radeon HD 7490M (Seymour XTX)				800	6.4	3.2	256	1	GDDR5 64-bit	950	30.4		9
Radeon HD 7510M (Thames LE)	January 2012	TeraScale 2[c] (40 nm)	400:20:8:5	450	9.0	3.6	360	1	DDR3 64-bit	800	12.8		11
Radeon HD 7530M (Thames LP)	January 2012	TeraScale 2[c] (40 nm)	400:24:8:5	450	9.0	3.6	360	1	DDR3 64-bit	900	14.4		11
Radeon HD 7550M (Thames Pro)	January 2012	TeraScale 2[c] (40 nm)	400:20:8:5	450 550	9.0 11.0	3.6 4.4	360 440	1	DDR3 GDDR5 64-bit	900 800	14.4 25.6		13
Radeon HD 7570M (Thames Pro)	January 2012	TeraScale 2[c] (40 nm)	400:20:8:5	450 650	9.0 13.0	3.6 5.2	360 520	1	DDR3 GDDR5 64-bit	900 800	14.4 25.6		13~15
Radeon HD 7590M (Thames XT)	January 2012	TeraScale 2[c] (40 nm)	480:24:8:6	600	14.4	4.8	576	1	GDDR5 64-bit	800	25.6		18
Radeon HD 7610M (Thames LE)	January 2012	TeraScale 2[c] (40 nm)	400:20:8:5	450	9.0	3.6	360	1	DDR3 128-bit	800	25.6		20
Radeon HD 7630M (Thames LP)	January 2012	TeraScale 2[c] (40 nm)	480:24:8:6	450	10.8	3.6	432	1	DDR3 128-bit	800	25.6		20~25
Radeon HD 7650M (Thames Pro)				450 550	10.8 13.2	3.6 4.4	432 528	1	DDR3 128-bit	800 800	25.6		20~25
Radeon HD 7670M (Thames Pro)				600	14.4	4.8	576	1	DDR3 GDDR5 128-bit	900	28.8 57.6		20~25
Radeon HD 7690M (Thames XT)				725 600	17.4 14.4	5.8 4.8	696 576	1 2	DDR3 GDDR5 128-bit	900 900	28.8 57.6		20~25
Radeon HD 7690M XT (Thames XTX)				725	17.4	5.8	696	1 2	GDDR5 128-bit	900	57.6		25
Radeon HD 7730M (Chelsea LP)	April 2012	GCN 1st gen (28 nm)	512:32:16:8	575 675	18.4 21.6	9.2 10.8	588.8 691.2	2	GDDR3 128-bit	900 900	28.8	PCIe 2.1 ×16	25~28
Radeon HD 7750M (Chelsea Pro)				575	18.4	9.2	588.8	1 2	GDDR5 128-bit	1000	64		28
Radeon HD 7770M (Chelsea XT)				675	21.6	10.8	691.2	1 2	GDDR5 128-bit	1000	64		32
Radeon HD 7850M (Heathrow Pro)	April 2012	GCN 1st gen (28 nm)	640:40:16:10	675	27	10.8	864	2	GDDR5 128-bit	1000	64	PCIe 3.0 ×16	40
Radeon HD 7870M (Heathrow XT)				800	32	12.8	1024	2	GDDR5 128-bit	1000	64		40–45
Radeon HD 7970M (Wimbledon XT)	April 2012	GCN 1st gen (28 nm)	1280:80:32:20	850	68	27.2	2176	2 4	GDDR5 256-bit	1200	153.6	PCIe 3.0 ×16	75

• v
• t
• e

1. Unified Shaders : Texture Mapping Units : Render Output Units
2. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
3. Lacks hardware video encoder

IGP (HD 7000G)

Main article: Radeon HD 7000 series

Model (Codename)	Launch	Architecture (Fab)	Core config[a]	Clock rate (MHz)		Fillrate		Processing power (GFLOPS)	Shared memory
				Core (MHz)	Boost (MHz)	Pixel (GP/s)	Texture (GT/s)		Bus type & width (bit)	Clock	Bandwidth (GB/s)
Radeon HD 7400G (Scrapper)	September 2012	TeraScale 3[b] (32 nm)	192:12:4	327	424	1.31	3.92	125.57	DDR3 128-bit	1333 to 2133	21.33–34.13
Radeon HD 7420G (Scrapper)	June 2012		128:8:4	480	655	1.92	3.84	122.88
Radeon HD 7500G (Scrapper)	May 2012		256:16:8	327	424	2.62	5.23	167.42
Radeon HD 7520G (Scrapper)	June 2012		192:12:4	496	685	1.98	5.95	190.46
Radeon HD 7600G (Devastator)	September 2012		384:24:8	320	424	2.56	7.68	245.76
Radeon HD 7620G (Devastator)	May 2012			360	497	2.88	8.64	276.48
Radeon HD 7640G (Devastator)			256:16:8	496	685	3.97	7.94	253.95
Radeon HD 7660G (Devastator)			384:24:8				11.9	380.93

• v
• t
• e

1. Unified Shaders : Texture Mapping Units : Render Output Units
2. Lacks hardware video encoder

Radeon HD 8000M series

Main article: Radeon HD 8000 series

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory[e]				TDP (W)
			Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (GiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)
Radeon HD 8550M / 8630M (Sun LE)	8 January 2013	GCN 1st gen (28 nm)	384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	1	DDR3 64	900	14.4	Unknown
Radeon HD 8570M / 8650M (Sun Pro)	8 January 2013		384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	1	GDDR5 64	1125	36	Unknown
Radeon HD 8670M (Mars XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	1	DDR3 64	900	14.4	Unknown
Radeon HD 8690M (Sun XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	1	GDDR5 64	1125	36	Unknown
Radeon HD 8730M (Mars LE)	8 January 2013		384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	2	DDR3 128	1000	32	Unknown
Radeon HD 8750M (Mars Pro)	8 January 2013		384:24:8	620–775 670–825	14.88 19.8	4.96 6.6	514.56 633.6	2	DDR3 GDDR5 128	1000	32 64	Unknown
Radeon HD 8770M (Mars XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	2	GDDR5 128	1125	72	Unknown
Radeon HD 8790M (Mars XTX)	8 January 2013		384:24:8	850 900	20.4 21.6	6.8 7.2	691.2	2	GDDR5 128	1125	72	Unknown
Radeon HD 8830M (Venus LE)	8 January 2013		640:40:16	575 625	23 25	9.2 10	800	2	DDR3 128	1000	32	Unknown
Radeon HD 8850M (Venus Pro)	8 January 2013		640:40:16	575–725 625–775	23 31	9.2 12.4	800 992	2	DDR3 GDDR5 128	1000 1125	32 72	Unknown
Radeon HD 8870M (Venus XT)	8 January 2013		640:40:16	725 775	29 31	11.6 12.4	992	2	DDR3 GDDR5 128	1000 1125	32 72	Unknown
Radeon HD 8970M (Neptune XT)	8 January 2013		1280:80:32	850 900	68 72	27.2 28.8	2304	2 4	GDDR5 256	1200	153.6	100

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
6. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon M200 series

Main article: Radeon 200 series § Mobile

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory				TDP
			Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (GiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)
Radeon R5 M230 (Jet Pro)	January 2014	GCN 1st gen (28 nm)	320:20:8:5	780 855	3.4	17.1	547	2 4	DDR3 64-bit	2000	16	Unknown
Radeon R5 M255 (Jet Pro)	June 2014		320:20:8:5	925 940	7.5	18.8	601	2 4	DDR3 64-bit	2000	16	Unknown
Radeon R7 M260 (Topaz)	June 2014		384:24:8:6	620 980	5.7 7.8	17.2 23.5	549.1 752.6	2 4	DDR3 64-bit	1800 2000	14.4 16	Unknown
Radeon R7 M260X (Opal)	June 2014		384:24:8:6	620 715	5.7	17.2	549	2 4	GDDR5 128-bit	4000	64	Unknown
Radeon R7 M265 (Opal XT)	May 2014		384:24:8:6	725 825	6.6	19.8	633.6	2 4	DDR3 64-bit	1800 2000	14.4 16	Unknown
Radeon R9 M265X (Venus Pro)	May 2014		640:40:16:10	575 625	10	25	800	2 4	GDDR5 128-bit	4500	72	Unknown
Radeon R9 M270X (Venus XT)	May 2014		640:40:16:10	725 775	12.4	31	992	2 4	GDDR5 128-bit	4500	72	Unknown
Radeon R9 M275X (Venus XTX)	May 2014		640:40:16:10	900 925	14.8	37	1184	2 4	GDDR5 128-bit	4500	72	50 W
Radeon R9 M280X (Saturn XT)	February 2015	GCN 2nd gen (28 nm)	896:56:16:14	1000 1100	17.6	61.6	1792	2 4	GDDR5 128-bit	6000	96	~75 W
Radeon R9 M290X (Neptune XT)	May 2014	GCN 1st gen (28 nm)	1280:80:32:20	850 900	28.8	72	2176 2304	4	GDDR5 256-bit	4800	153.6	100 W
Radeon R9 M295X (Amethyst XT)	November 2014	GCN 3rd gen (28 nm)	2048:128:32:32	750 800	25.6	102.4	3276.8	4	GDDR5 256-bit	5500	176	250 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon M300 series

Main article: Radeon 300 series § Mobile

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory				TDP
			Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (GiB)	Bus type & width	Clock (MT/s)	Band- width (GB/s)
Radeon R5 M330[236] (Exo Pro)	2015	GCN 1st gen (28 nm)	320:20:8	Unknown 1030	8.2	20.6	659.2	2 4	DDR3 64-bit	1800 2000	14.4 16	18 W
Radeon R5 M335[236] (Exo Pro)	2015		320:20:8	Unknown 1070	8.6	21.4	684.8	2 4	DDR3 64-bit	2200	17.6	Unknown
Radeon R7 M360[237] (Meso XT)	2015		384:24:8	Unknown 1125	9	27	864	2 4	DDR3 64-bit	2000	16	Unknown
Radeon R9 M365X[238] (Strato Pro)	2015		640:40:16	Unknown 925	14.8	37	1184	4	GDDR5 128-bit	4500	72	50 W
Radeon R9 M370X[238] (Strato Pro)	May 2015		640:40:16	800	12.8	32	1024	2	GDDR5 128-bit	4500	72	40–45 W
Radeon R9 M375[238] (Strato Pro)	2015		640:40:16	Unknown 1015	16.2	40.6	1299.2	4	GDDR5 128-bit	4400	35.2	Unknown
Radeon R9 M375X[238] (Strato Pro)	2015		640:40:16	Unknown 1015	16.2	40.6	1299.2	4	GDDR5 128-bit	4500	72	Unknown
Radeon R9 M380[238] (Strato Pro)	2015		640:40:16	Unknown 900	14.4	36	1152	4	GDDR5 128-bit	6000	96	Unknown
Radeon R9 M385X[238] (Strato)	2015	GCN 2nd gen (28 nm)	896:56:16	Unknown 1100	17.6	61.6	1971.2	4	GDDR5 128-bit	6000	96	~75 W
Radeon R9 M390[238] (Pitcairn)	June 2015	GCN 1st gen (28 nm)	1024:64:32	Unknown 958	30.7	61.3	1962	2	GDDR5 256-bit	5460	174.7	~100 W
Radeon R9 M390X[238] (Amethyst XT)	2015	GCN 3rd gen (28 nm)	2048:128:32	Unknown 723	23.1	92.5	2961.4	4	GDDR5 256-bit	5000	160	125 W
Radeon R9 M395[238] (Amethyst Pro)	2015		1792:112:32	Unknown 834	26.6	93.4	2989.0	2	GDDR5 256-bit	5460	174.7	125 W
Radeon R9 M395X[238] Amethyst XT)	2015		2048:128:32	Unknown 909	29.1	116.3	3723.3	4	GDDR5 256-bit	5460	174.7	125 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon M400 series

Main article: Radeon 400 series § Mobile

Model (Codename)	Launch	Architecture & Fab	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory				TDP
			Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Bus type & width	Size (GiB)	Clock (MHz)	Band- width (GB/s)
Radeon R5 M420[239] (Jet Pro)	15 May 2016	GCN 1st gen 28 nm	320:20:8	780 855	15.6 17.1	6.24 6.84	499 547	DDR3 64-bit	2	1000	16.0	~20 W
Radeon R5 M430[240] (Exo Pro)	15 May 2016		320:20:8	1030 ?	20.6	8.2	659.2 659.2	DDR3 64-bit	2	1000	14.4	18 W
Radeon R7 M435[241] (Jet Pro)	15 May 2016		320:20:8	780 855	15.6 17.1	6.24 6.84	499 547	GDDR5 64-bit	4	1000	32	~20 W
Radeon R7 M440[242] (Meso Pro)	15 May 2016		320:20:8	1021 ?	20.4	8.17	653 653	DDR3 64-bit	4	1000	16	~20 W
Radeon R7 M445[243] (Meso Pro)	14 May 2016		320:20:8	780 920	15.6 18.4	6.24 7.36	499 589	GDDR5 64-bit	4	1000	32	~20 W
Radeon R7 M460[244][245] (Meso XT)	April 2016		384:24:8	1100 1125	26.4 27.0	8.8 9.00	844 864	DDR3 64-bit	2	900	14.4	Unknown
Radeon RX 460[246] (Baffin)	August 2016	GCN 4th gen 14 nm	896:56:16	Unknown	Unknown	Unknown	Unknown	GDDR5 128-bit	2	1750	112	35 W?
Radeon R7 M465[247][248] (Litho XT)	May 2016	GCN 1st gen 28 nm	384:24:8	825 960	19.8 23.0	6.6 7.68	634 737	GDDR5 128-bit	4	1150	32	Unknown
Radeon R7 M465X[249] (Tropo XT)	May 2016		512:32:16	900 925	28.8 29.6	14.4 14.80	921 947	GDDR5 128-bit	4	1125	72	Unknown
Radeon R9 M470[250] (Strato Pro)	May 2016	GCN 2nd gen 28 nm	768:48:16	900 1000	43.2 48.0	14.4 16.00	1382 1536	GDDR5 128-bit	4	1500	96	~75 W
Radeon R9 M470X[251] (Strato XT)	May 2016		896:56:16	1000 1100	56.0 61.6	16.00 17.60	1792 1971	GDDR5 128-bit	4	1500	96	~75 W
Radeon RX 470[252] (Ellesmere Pro)	August 2016	GCN 4th gen 14 nm	2048:128:32	Unknown	Unknown	Unknown	Unknown	GDDR5 256-bit	4	1650	211	85 W?
Radeon RX 480M (Baffin)	TBA		1024:xx:xx	Unknown	Unknown	Unknown	Unknown	GDDR5 128-bit	Unknown	Unknown	Unknown	35 W
Radeon R9 M485X[253] (Antigua XT)	May 2016	GCN 3rd gen 28 nm	2048:128:32	723	92.5	23.14	2961	GDDR5 256-bit	8	1250	160	~100 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon M500 series

Main article: Radeon 500 series

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory				TDP
			Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Bus type & width	Size (GiB)	Clock (MHz)	Band- width (GB/s)
Radeon 520[254] (Banks)	18 April 2017	GCN 1st gen (28 nm)	320:20:8	1030	20.6	8.2	659	DDR3 64-bit	2	1000	16.0	50 W
								GDDR5 64-bit		1125	36
Radeon 530[255] (Weston)		GCN 3rd gen (28 nm)	384:24:8	730 1024	24.6	8.2	786	DDR3 64-bit		900	14.4
Radeon 530X[256] Radeon 535[257] (Polaris 24 XT)								GDDR5 64-bit		1125	36
Radeon RX 540[258] (Lexa Pro)	11 November 2017	GCN 4th gen (14 nm)	512:32:16	1124 1219	39	19.5	1248	GDDR5 128-bit		1500	96
Radeon 540X[259] (Polaris 23 XL)	11 April 2018
Radeon RX 550[260] (Lexa Pro)	2 July 2017		640:40:16	1100 1287	51.5	20.6	1647
Radeon 550X[261] (Polaris 23 XT)	11 April 2018
Radeon RX 560[262][263] (Baffin XT)	5 January 2017		896:56:16	784 1032	57.8	16.5	1849		4	1710	109.4	55 W
				1000 1053	59	16.9	1887			1500	96
			1024:64:16	1090 1202	77	19.2	2462					65 W
Radeon RX 560X[264] (Polaris 31 XL)	9 January 2019		896:56:16	1223	68.5	19.6	2192			1750	112
Radeon RX 570[265] (Ellesmere Pro)	10 December 2017		2048:128:32	926 1206	154.4	38.6	4940	GDDR5 256-bit	8	1650	211	85 W
Radeon RX 580[266] (Polaris 20 XT)	18 April 2017		2304:144:32	1000 1077	155.1	34.5	4963			2000	256	100 W
Radeon RX 580X[267] (Polaris 20 XT)	11 April 2018

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon 600 series

Main article: Radeon 600 series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon 610 (Banks)[268]	Aug 13, 2019 OEM[269]	GCN 1[270] TSMC 28 nm	6.9×108 56 mm2	320:20:4 5 CU	1030	20.60	8.24	659.2	41.20	2 4	36.0	GDDR5 64-bit	4500	50 W	PCIe 3.0 ×8
Radeon 620 (Polaris 24)[271]		GCN 3[272] TSMC 28 nm	1.55×109 125 mm2	320:20:8 6 CU	730 1024	17.52 24.58	5.84 8.19	560.6 786.4	35.04 49.15		14.4	DDR3 64-bit	1800
				384:24:8 6 CU							36.0	GDDR5 64-bit	4500
Radeon 625 (Polaris 24)[273]
Radeon 630 (Polaris 23)[274][275]		GCN 4 GloFo 14 nm[f]	2.2×109 103 mm2	512:32:8 8 CU	1082 1219	34.62 38.98	8.65 9.75	1,108 1,248	69.24 78.01		48.0		6000
Radeon RX 640 (Polaris 23)[276][277]				512:40:16 8 CU	1082 1287	43.28 51.48	17.31 20.59	1,385 1,647	86.56 102.9		56.0		7000
				640:40:16 10 CU

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)
6. GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.^[101]

Radeon RX 5000M series

Main article: AMD Radeon RX 5000 series § Mobile

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 5300M (Navi 14)[278][279]	Nov 13, 2019	RDNA TSMC N7	6.4×109 158 mm2	1408:88:32 22 CU	1000 1445	88.0 127.2	32.0 46.2	5,632 8,138	2,816 4,069	176.0 254.3	3	168	GDDR6 96-bit	14000	65 W	PCIe 4.0 ×8
Radeon RX 5500M (Navi 14)[278][280]	Oct 7, 2019				1375 1645	121.0 144.8	44.0 52.6	7,744 9,265	3,872 4,632	242.0 289.5	4	224	GDDR6 128-bit		85 W
Radeon RX 5600M (Navi 10)[278][281]	Jul 7, 2020		10.3×109 251 mm2	2304:144:64 36 CU	1035 1265	149.0 182.2	66.2 80.9	9,539 11,658	4,769 5,829	298.0 364.3	6	288	GDDR6 192-bit	12000	85 W	PCIe 4.0 ×16
Radeon RX 5700M (Navi 10)[278][282]	Mar 1, 2020				1465 1720	210.9 247.7	93.7 110.1	13,501 15,852	6,751 7,926	421.9 495.4	8	384	GDDR6 256-bit		120 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon RX 6000M series

Main article: AMD Radeon RX 6000 series § Mobile

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Infinity Cache	Memory				HW Decoder			HW Encoder			TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)	AV1	H265	4K H264	AV1	H265	4K H264
Radeon RX 6300M (Navi 24)[f][283]	Jan 4, 2022	RDNA 2 TSMC N6	5.4×109 107 mm2	768:64:32:12 12 CU	1512	97.76	48.38	6,270	3,130	195.6	8 MB	2 GB	64	GDDR6 32-bit	16000							25 W	PCIe 4.0 ×4
Radeon RX 6450M (Navi 24)[284]	Jan 4, 2023				2220	118.10	71.04	7,600	3,780	236.3	16 MB	4 GB	128	GDDR6 64-bit								50 W
Radeon RX 6550S (Navi 24)[285]				1024:64:32:16 16 CU	2170	154.20	69.44	9,900	4,900	306.3
Radeon RX 6500M (Navi 24)[f][286]	Jan 4, 2022				2191	155.7	70.11	9,970	4,980	311.2
Radeon RX 6550M (Navi 24)[287]	Jan 4, 2023				2560	182.10	81.92	11,600	5,800	362.5			144		18000							80 W
Radeon RX 6600S (Navi 23)[288]	Jan 4, 2022	RDNA 2 TSMC N7	11.06×109 237 mm2	1792:128:64:28 28 CU	1881	244.2	120.3	15,630	7,810	448.1	32 MB		224	GDDR6 128-bit	14000								PCIe 4.0 ×8
Radeon RX 6700S (Navi 23)[289]					1890	247.5	120.9	15,840	7,920	495.0		8 GB
Radeon RX 6600M (Navi 23)[290]	May 31, 2021				2177	274.2	139.3	17,550	7,800	487.5												100 W
Radeon RX 6650M (Navi 23)[291]	Jan 4, 2022				2222	276.6	139.3	17,700	8,850	553.1			256		16000							120 W
Radeon RX 6800S (Navi 23)[292]				2048:128:64:32 32 CU	1975	288.0	134.4	18,430	9,220	576.5												100 W
Radeon RX 6650M XT (Navi 23)[293]					2162	311.5	142.2	19,940	9,970	623.1												120 W
Radeon RX 6700M (Navi 22)[294]	May 31, 2021		17.2×109 335 mm2	2304:144:64:36 36 CU	2300	331.4	147.2	21,209	10,605	662.1	80 MB	10 GB	320	GDDR6 160-bit								135 W	PCIe 4.0 ×16
Radeon RX 6800M (Navi 22)[295]				2560:160:64:40 40 CU	2300	368.0	147.2	23,550	11,780	736.2	96 MB	12 GB	384	GDDR6 192-bit								145+ W
Radeon RX 6850M XT (Navi 22)[296]	Jan 4, 2022				2580	415.6	157.6	26,430	13,209	825.6			432		18000							165 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units CU
6. Lacks hardware video encoder.

Radeon RX 7000M series

Main article: AMD Radeon RX 7000 series § Mobile

Model (Code name)	Release date	Architecture & fab	Chiplets	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (TFLOPS)[e]			Infinity Cache	Memory				TDP	Interface
					Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half[g]	Single	Double		Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon RX 7600S (Navi 33)[297]	Jan 4, 2023	RDNA 3 TSMC N6	Monolithic	13.3×109 204 mm2	1792:112:64:28:56 28 CU	1500 2200	168.0 246.4	96.00 140.8	10.75 15.77	10.75 15.77	0.168 0.246	32 MB	8 GB	256	GDDR6 128-bit	16000	75 W	PCIe 4.0 ×8
Radeon RX 7600M (Navi 33)[298]						1500 2410	168.0 269.9	96.0 154.2	10.75 17.28	10.75 17.28	0.168 0.270						90 W
Radeon RX 7600M XT (Navi 33)[299]					2048:128:64:32:64 32 CU	1500 2615	192.0 334.1	96.00 167.0	12.29 21.42	12.29 21.42	0.192 0.335			288		18000	120 W
Radeon RX 7700S (Navi 33)[300]						1500 2500	192.0 320.0	96.0 160.0	12.29 20.48	12.29 20.48	0.192 0.320						100 W
Radeon RX 7800M (Navi 32)[301]	Sep 11, 2024	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 3 × MCD	28.1×109 346 mm2	3840:240:96:60:120 60 CU	2335	560.4	224.2	35.87	35.87	0.560	48 MB	12 GB	432	GDDR6 192-bit		180 W	?
Radeon RX 7900M (Navi 31)[302]	Oct 19, 2023		1 × GCD 4 × MCD	57.7×109 529 mm2	4608:288:192:72:144 72 CU	1825 2090	525.6 601.9	350.4 401.3	33.64 38.52	33.64 38.52	0.526 0.602	64 MB	16 GB	576	GDDR6 256-bit			PCIe 4.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.
6. Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
7. Officially declared half-precision performance is twice of the one shown here due to being based on different operation (a×b+c×d+e).

Workstation GPUs

FireGL series

Main article: ATI FireGL

Model	Launch	Micro-archi-tecture	Core	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config	Fillrate		Memory				Processing power (GFLOPS)	API compliance (version)			Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Direct3D	OpenGL	Vulkan
FireGL 8700	2001	R200	Radeon 8500	150	AGP	250	270	2:4:8:41	1	2	64	8.64	DDR	64 × 2	Unknown	8.1	1.4	—
FireGL 8800						300	290		1.2	2.4	128	9.28			Unknown
FireGL T2-64	2003	R300	Radeon 9600 Pro	130		325	200	2:4:4:41	1.3	1.3	64	6.4		128	Unknown	9.0	2.0
FireGL T2-128						400	320		1.6	1.6	128	10.2			Unknown
FireGL Z1-128	2002		Radeon 9500 Pro	150		325	310	4:4:4:41	1.3	1.3		19.8		256	Unknown
FireGL X1-128			Radeon 9700					4:8:8:81	2.6	2.6					Unknown
FireGL X1-256			Radeon 9700 Pro		AGP Pro	325					256				Unknown
FireGL X2-256	2003		Radeon 9800 Pro		AGP	380	350		3.04	3.04		22.4	DDR2		Unknown
FireGL X2-256T			Radeon 9800 XT			412	344		3.3	3.3		22.0			Unknown
FireGL X3-256	2004		Radeon X800 XT	130		450	450	6:12:12:121	5.4	5.4		28.8	GDDR3		Unknown	9.0b
FireGL V3100	2005		Radeon X300 XT	110	PCIe x16	400	200	2:4:4:41	1.6	1.6	128	6.4	DDR	128	Unknown	9.0
FireGL V3200			Radeon X600 XT	130		500	400		2	2		12.8	DDR2		Unknown	9.0b
FireGL V3300	2006	R500	Radeon 1300 Pro	90		600			2.4	2.4	128	6.4	GDDR2	64	Unknown	9.0c
FireGL V3350											256				Unknown
FireGL V3400			Radeon 1600 Pro/XT			500	500	5:12:4:41	2	2	128	16.0	GDDR3	128	Unknown
FireGL V3600[303]	2007	Tera-Scale 1	RV630 GL, HD 2600 Pro	65		600	500	1202(24×5):8:4:3	2.4	4.8	256				144	10	3.3		Shader Model 4.0, APP Stream
FireGL V5000	2005	R400	Radeon X700 Pro/XT	130		425	430	6:8:8:81	3.4	3.4	128	13.6			Unknown	9.0b	2.0
FireGL V5100			Radeon X800 Pro			450	350	6:12:12:121	5.4	5.4		22.4	DDR	256	Unknown
FireGL V5200		R500	Radeon X1600 XT	90		600	700	5:12:4:41	2.4	2.4	256	22.4	GDDR3	128	Unknown	9.0c
FireGL V5600[304]	2007	Tera-Scale 1	R630 GL, HD 2600 XT	65	PCIe	800	1100	1202(24×5):8:4:3	3.2	6.4	512	35.2	GDDR4		192	10	3.3		Shader Model 4.0, APP Stream
FireGL V7100	2005	R400	Radeon X800 XT	130		500	450	6:16:16:161	8	8	256	28.8	GDDR3	256	Unknown	9.0c	2.0
FireGL V7200	2006	R500	Radeon X1800 XT	90	PCIe ×16	600	650		9.6	9.6		41.6			Unknown
FireGL V7300[305]			R520 GL, X1800 XT		PCIe						512				Unknown
FireGL V7350[306]											1024				Unknown
FireGL V7400	2006 (canceled)		Radeon X1950 Pro	80		550?	650?	8:36:16:161	19.8?	19.8?	512?	41.6?			Unknown				never released, superseded by 2007 series
FireGL V7600[307]	2007	Tera-Scale 1	R600 GL, HD 2900 GT			600	800	2402(48×5):12:12:3	9.6	9.6	512	51.2			288	10	3.3		Shader Model 4.0, APP Stream
FireGL V7700[308]	2007 (2008)		R670 GL, HD 3870	55	PCIe 2.0	775	1125	3202(64×5):16:16:4	12.4	12.4		72	GDDR4		496	10.1 (SM4.1)			DisplayPort. Can do double precision computation via the AMD Stream SDK.
FireGL V8600[309]	2007		R600 GL, HD 2900 XT	80	PCIe	688	868	3202(64×5):16:16:4	11.01	11.01	1024	111.1[310]		512	440.32	10			Shader Model 4.0, APP Stream
FireGL V8650[311]											2048	111.1

¹ Vertex shaders : Pixel shaders : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units : Compute Units

FireMV (Multi-View) series

Main article: ATI FireMV

Model	Launch	Core	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate (GT/s)	Memory				API compliance (version)		TDP / idle (Watts)	Notes
								Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
FireMV 2200 PCI[312]	January 2006	RV280 GL	PCI	240	200	1:4:4:4	0.96	64	3.2	DDR	64	8.1	1.4	15	DMS-59 for dual DVI-D output
FireMV 2200 PCIe[313]		RV370	PCIe ×16	324	196	2:4:4:4	1.296	128				9.0	2.1
FireMV 2260[314]	January 2008	RV620	PCIe 2.0 ×1/×16, PCI	600	500	40(8×5):4:4	2.4	256	32	DDR2	256	10.1[315]	3.3	15/8	Dual DisplayPort (with adapters: DVI-D)
FireMV 2400 PCI[316]		RV380	PCI	500		2:4:4:4	2.0	128	16	DDR	128	9.0b	2.1	20	2× VHDCI for quad DVI-D output, VGA
FireMV 2400 PCIe[317]			PCIe ×1	500				256		DDR3

¹ Vertex shaders : Pixel shaders : Texture mapping unit : Render output units
² Unified shaders : Texture mapping unit : Render output units

FirePro (Multi-View) series

Model	Launch	Core	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		TDP / idle (watts)	Notes
										Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL (OpenCL)
FirePro 2250[318]	2007-01-01	RV516	80	107	100	PCIe x1/x16	600	500	2:4:4:4	2.4	0.3	256	32	DDR2	256	9.0c	2.1 (no)	20/11	DMS-59 for dual DVI-D output
FirePro 2270[319]	2011-01-31	Cedar GL (RV810)	40	292	59	PCIe 2.1 x1/x16		600	80(16×5):8:4:1		4.8	512 1024	9.6	GDDR3	64	11.0	4.3 (1.2)	15/8 17/8	DMS-59 for dual output: DP or DVI-I or D-sub
FirePro 2450 Multi-View[320]	2009-01-01	2× RV620 (Terascale 1)	55	2× 181	2× 61	PCIe 2.0 ×1/×16			2× 40(8×5):4:4:1			512	38.4		256	10.1	3.3 (APP)	36/18	2× VHDCI for quad output: DVI-I or D-sub
FirePro 2460 Multi-View[321][322]	2010-04-01	Cedar GL (RV810) (Tera-scale2)	40	292	59	PCIe 2.1 ×16	500	500	80(16×5):8:4:1	2.0	4.0		32	GDDR5	64	11.0	4.3 (1.2)	17/13	4× Mini DP for quad output: DP or DVI-D, UVD2, PowerPlay, Eyefinity

FirePro 3D series (V000)

Model	Launch	Microarchitecture	Code name	Fab (nm)	Transistors (million)	Die size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
								Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro 3D V3700[323]	August 8, 2008	Terascale 1	RV620 PRO[324]	55	181	67	PCIe 2.0 ×16	800	950	40(8×5):4:4:2	3.2	3.2	256	15.2	GDDR3	64	64	-	10.1	3.3 SM4.1	APP Stream only	—	32	UVD+, PowerPlay
FirePro 3D V3750[325]	September 11, 2008		RV730 PRO		514	146		550	750	320(64×5):32:8:4	4.4	17.6		24		128	352			3.3	1.0		48
FirePro 3D V3800[326][327]	April 26, 2010	TeraScale 2	Redwood Pro GL (RV830)	40	627	104	PCIe 2.1 ×16	650	900	400(80×5):20:8:5	5.2	13	512	14.4		64	520	?	11.0	4.3 SM5.0	1.2		43	UVD2, PowerPlay, Eyefinity
FirePro 3D V4800[328][329]			Redwood XT GL (RV830)		672			775	9002		6.2	15.5	1024	57.6	GDDR52	128	620			4.3			69
FirePro 3D V5700[330]	August 8, 2008	TeraScale 1	RV730 XT	55	514	146	PCIe 2.0 ×16	700	900	320(64×5):32:8:4	5.6	22.4	512	28.8	GDDR3		448	-	10.1	3.3	1.0		58	UVD2, PowerPlay
FirePro 3D V5800[326][331]	April 26, 2010	TeraScale 2	Juniper XT GL (RV840)	40	1040	166	PCIe 2.1 ×16		10002	800(160×5):40:16:10	11.2	28	1024	64	GDDR52		1120	-	11.0	4.3	1.2		74	UVD2, PowerPlay, Eyefinity
FirePro 3D V7750[332]	March 27, 2009	TeraScale 1	RV730 XTX	55	514	146	PCIe 2.0 ×16	800	900	320(64×5):32:8:4	6.4	25.6		28.8	GDDR3		512	-	10.1	3.3	1.0		76	UVD2, PowerPlay
FirePro 3D V7800[328][333]	April 26, 2010	TeraScale 2	Cypress Pro GL (RV870)	40	2154	334	PCIe 2.1 ×16	700	10002	1440(288×5):72:32:18	22.4	50.4	2048	128	GDDR52	256	2016	403.2	11.0	4.3	1.2		138	UVD2, PowerPlay, Eyefinity
FirePro 3D V8700[334]	September 11, 2008	TeraScale 1	RV770 XT	55	956	256		750	8502	800(160×5):40:16:10	12	30	1024	108.8			1200	240	10.1	3.3	1.0		151	UVD2, PowerPlay
FirePro 3D V8750[335]	July 28, 2009								9002				2048	115.2				240					154
FirePro 3D V8800[336]	April 7, 2010	TeraScale 2	Cypress XT GL (RV870)	40	2154	334		825	11502	1600(320×5):80:32:20	26.4	66		147.2			2640	528	11.0	4.3	1.2		208	UVD2, PowerPlay, Eyefinity
FirePro 3D V9800[337]	September 9, 2010							850			27.2	68	4096				2720	544					225

¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory
³ Windows 7, 8.1, 10 Support for Fire Pro Cards with Terascale 2 and later by firepro driver 15.301.2601^[338]

FirePro series (Vx900)

Model	Launch	Microarchitecture	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro V3900[339]	February 7, 2012	TeraScale 2	Turks GL	40	PCIe 2.1 ×16	650	900	480(96×5):24:8:6	5.2	15.6	1	28.8	GDDR3	128	624	-	11.0	4.3	1.2	—	50	HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V4900[340]	November 1, 2011		Turks XT GL			800	1000		6.4	19.2		64	GDDR52		768						<75 max
FirePro V5900[341]	May 24, 2011	TeraScale 3	Cayman LE GL			600	5002	512(128×4):32:32:8	19.2		2			256	610	154
FirePro V7900[342]			Cayman Pro GL			725	12502	1280(320×4):80:32:20	23.2	58		160			1860	464					<150 max

¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ Support for Windows 7, 8.1 for OpenGL 4.4 and OpenCL 2.0, when Hardware is prepared with firepro driver 14.502.1045^[343]

FirePro Workstation series (Wx000)

• Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher.^[344][345]
• Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs.^[346]

Model	Launch	Microarchitecture	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro W600[347]	June 13, 2012	GCN 1st gen	Cape Verde Pro GL	28	PCIe 3.0 x16	750	1000	512:32:16:8	12.0	24.0	2	64	GDDR5	128	768	Up to 55	11.1/12	4.5	1.2	1.0	75	6× Mini DisplayPort
FirePro W5000[348]			Pitcairn LE GL			825	800	768:48:32:12	26.4	39.6		102.4		256	1267.2	79.2					<75	2× DisplayPort, 1× DVI-I
FirePro W7000[349]			Pitcairn XT GL			950	1200	1280:80:32:20	30.4	76.0	4	153.6			2432	152					<150	4× DisplayPort
FirePro W8000[350]	June 14, 2012		Tahiti PRO GL			900	1375	1792:112:32:28	28.8	100.8		176			3225.6	806.4					<225	ECC RAM, 4× DisplayPort + SDI-Link
FirePro W9000[351][352]			Tahiti XT GL			975	1375	2048:128:32:32	31.20	124.8	6	264		384	3993.6	998.4					274	ECC RAM, Six mini-DisplayPorts + SDI-Link

¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs^[353]

FirePro D-Series

In 2014, AMD released the D-Series specifically for Mac Pro workstations.^[354]

Model	Launch	Microarchitecture	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro D300[355]	January 18, 2014	Southern Islands	Pitcairn XT GL	28	PCIe 3.0 ×16	850	1270	1280:80:32:20			2	162.6	GDDR5	256	2176	136	11.1	4.6	1.2	1.1.101	150
FirePro D500[356]	January 18, 2014		Tahiti LE GL			725	1270	1536:96:32:24			3	243.8		384	2227	556.8					274
FirePro D700[357]	January 18, 2014		Tahiti XT GL			850	1370	2048:128:32:32			6	263			3482	870.4

¹ Unified shaders : Texture mapping units : Render output units : compute units

FirePro Workstation series (Wx100)

• Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher.^[344][345] OpenCL 2.1 and 2.2 possible for all OpenCL 2.0-Cards with Driver Update in Future (Khronos). Linux Support for OpenCL is limited with AMDGPU Driver 16.60 actual to Version 1.2.^[358]
• Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs.^[346]

Model	Launch	Micro-archi-tecture	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro W2100[359]	August 13, 2014	GCN 1st gen	Oland XT	28	PCIe 3.0 x8	630	900	320:20:8:5	5.04	12.6	2	28.8	DDR3	128	403.2	25.5	11.2a/12.0	4.5	2.0 (new)	1.0	<26	2× Standard DisplayPort DP 1.2a outputs
FirePro W4100[360]			Cape Verde		PCIe 3.0 ×16	630	1125	512:32:16:8	10.08	20.16		72	GDDR5		645.1	40.3					<50	4× Standard Mini-DP 1.2a outputs
FirePro W5100[361]		GCN 2nd gen	Bonaire Pro			930	1500	768:48:16:12	14.88	44.64	4	96			1430	89.2	11.2b/12.0		2.0		<75	DirectGMA, GeometryBoost, 4 DP 1.2a, including Adaptive-Sync and HBR2
FirePro W7100[362]		GCN 3rd gen	Tonga Pro GL			920	1400	1792:112:32:28	29.4	103	8	160		256	3297	206				1.1	<150
FirePro W8100[363]	June 26, 2014	GCN 2nd gen	Hawaii Pro GL			824	1250	2560:160:64:40	52.7	145		320		512	4218.9	2109.45				1.0	220	ECC RAM, 4 DP + SDI-Link
FirePro W9100[364]	March 26, 2014		Hawaii XT			930	1250	2816:176:64:44	59.5	163.7	16 32	320			5237.8	2618.9			2.0[365]		275	ECC RAM, 6× Mini DisplayPort + SDI-Link

¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs^[353]

FirePro Workstation series (Wx300)

• Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs.^[346]

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
FirePro W4300[366]	December 1, 2015	Bonaire PRO (GCN 2nd Gen)	28	PCIe 3.0 x16	930	1500	768:48:16:12[367]	14.88	44.64	4	96	GDDR5	128	1428.5	89.3	11.2/12.0 SM 5.0	4.5	2.0 (2.1 beta, 2.2 possible)	1.0	<50	4 Mini DisplayPort 1.2a outputs, low profile

Radeon PRO series

Main article: Radeon PRO series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro Duo (Fiji)[368][369]	Apr 26, 2016 $1,499 USD	GCN 3 TSMC 28 nm	2× 8.9×109 596 mm2	2× 4096:256:64 64 CU	1000	2× 256.0	2× 64.00	2× 8,192	2× 8,192	2× 512.0	2× 4 GB	2× 512	HBM 2× 4096-bit	1000	350 W	PCIe 3.0 ×16	3× DP 1.2 1× HDMI 1.4a
Radeon Pro Duo (Polaris 10)[370][371]	Apr 24, 2017 $999 USD	GCN 4 GloFo 14 nm	2× 5.7×109 232 mm2	2× 2304:128:32 36 CU	1243	2× 179.0	2× 39.78	2× 5,728	2× 5,728	2× 358.0	2× 16 GB	2× 224	GDDR5 2× 256-bit	7000	250 W		3× DP 1.4a 1× HDMI 2.0b
Radeon Pro SSG (Fiji)[372][373][374]	Jul 26, 2016 prototype only $9,999 USD	GCN 3 TSMC 28 nm	8.9×109 596 mm2	4096:256:64 64 CU	1050	268.8	67.20	8,601	8,601	537.6	4 GB +1 TB SSD	512	HBM + SSG 4096-bit	1000	200 W		4× DP 1.2
Radeon Pro SSG (Vega 10)[375][376][377][378][379]	Aug 8, 2017 $6,999 USD	GCN 5 GloFo 14 nm	12.5×109 495 mm2	4096:256:64 64 CU	1440 1500	368.6 384.0	92.16 96.00	23,593 24,576	11,796 12,288	737.2 768.0	16 GB +2 TB SSD	484	HBM2 + SSG 2048-bit	1890	230 W		6× miniDP 1.4a
Radeon Vega Frontier Edition (Vega 10)[380][381][382]	Jun 27, 2017 $999 USD				1382 1600	353.8 409.6	88.4 102.4	22,643 26,214	11,321 13,107	707.6 819.2	16 GB		HBM2 2048-bit		300 W		3× DP 1.4a 1× HDMI 2.0b
Radeon Vega Frontier Edition (Liquid-cooled) (Vega 10)[383][381][384]	Jun 27, 2017 $1,499 USD														375 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro WX x100 series

Main article: Radeon Pro WX series

• Vulkan 1.1 possible for GCN with Radeon Pro software 18.Q1.1 or higher.^[346]

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro WX 2100 (Polaris 12)[385][386][387]	Jun 1, 2017 $149 USD	GCN 4 GloFo 14 nm	2.2×109 103 mm2	512:32:16 8 CU	925 1219	29.6 39.0	14.8 19.5	947 1,250	947 1,250	59.2 78	2	48	GDDR5 64-bit	6000	35 W	PCIe 3.0 ×8	1× DP 1.4a 2× miniDP 1.4a
Radeon Pro WX 3100 (Polaris 12)[385][388][389]	Jun 1, 2017 $199 USD										4	96	GDDR5 128-bit		50 W
Radeon Pro WX 4100 (Polaris 11)[390][391][392][393]	Nov 10, 2016 $399 USD		3.0×109 123 mm2	1024:64:16 16 CU	1125 1201	72 76.9	18 19.2	2,304 2,460	2,304 2,460	144 154		96		7000			4× miniDP 1.4a
Radeon Pro WX 5100 (Polaris 10)[390][391][394][395]	Nov 18, 2016 $499 USD		5.7×109 232 mm2	1792:112:32 28 CU	713 1086	79.85 121.6	22.8 34.75	2,555 3,892	2,555 3,892	159.7 243.3	8	160	GDDR5 256-bit	5000	75 W	PCIe 3.0 ×16	4× DP 1.4a
Radeon Pro WX 7100 (Polaris 10)[390][396][391][397][398]	Nov 10, 2016 $799 USD			2304:144:32 36 CU	1188 1243	171 179	38 39.78	4,150 5,728	5,474 5,728	342.1 358		224		7000	130 W
Radeon Pro WX 9100 (Vega 10)[399][400][401][402][403]	Sep 13, 2017 $2,199 USD	GCN 5 GloFo 14 nm	12.5×109 495mm2	4096:256:64 64 CU	1200 1500	307.2 384.0	76.8 96.0	19,660 24,576	9,830 12,288	614.4 768	16	484	HBM2 2048-bit	1890	230 W		6× miniDP 1.4a

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro WX x200 series

Main article: Radeon Pro WX series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro WX 3200 (Polaris 23)[404][405]	Jul 2, 2019 $199 USD	GCN 4 GloFo 14 nm	2.2×109 103mm2	640:32:16 10 CU	1295	41.44	20.72	1,658	1,658	103.6	4	96	GDDR5 128-bit	6000	50 W	PCIe 3.0 ×8	4× mini-DP 1.4a
Radeon Pro WX 8200 (Vega 10)[406][407]	Aug 13, 2018 $999 USD	GCN 5 GloFo 14 nm	12.5×109 495mm2	3584:224:64 56 CU	1200 1500	268.8 336.0	76.8 96.00	17,203 21,504	8,601 10,752	537.6 672.0	8	512	HBM2 2048-bit	2000	230 W	PCIe 3.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro Vega series

Main article: Radeon Pro Vega series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TBP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro Vega II (Vega 20)[408][409][410]	2019 $2,800 USD	GCN 5 TSMC 7 nm	13.23×109 331 mm2	4096:256:64 64 CU	1720	440.3	110.1	28,180	14,090	880	32	1024	HBM2 4096-bit	2000	475 W	PCIe 3.0 ×16	4× Thunderbolt 3 (USB Type-C) 1× HDMI 2.0b
Radeon Pro Vega II Duo (Vega 20)[408][411][412]	2019 $5,600 USD			2× 4096:256:64 64 CU	1720	2× 440.3	2× 110.1	2× 28,180	2× 14,090	2× 880	2× 32	2× 1024	HBM2 2× 4096-bit	2000

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro 5000 series

Main article: Radeon Pro 5000/5000M series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro 5300 (Navi 14)[413][414]	Aug 4, 2020	RDNA TSMC N7	6.4×109 158 mm2	1280:80:32 20 CU	1000 1650	80 132	32 52.8	5,120 8,448	2,560 4,224	160 264	4	224	GDDR6 128-bit	14000	130 W	PCIe 4.0 ×8
Radeon Pro 5500 XT (Navi 14)[413][415]				1536:96:32 24 CU	1187 1757	114 168.7	38 56.2	7,292 10,796	3,646 5,398	227.9 337.3	8
Radeon Pro 5700 (Navi 10)[413][416]			10.3×109 251 mm2	2304:144:64 36 CU	1243 1350	179 194.4	79.6 86.4	11,456 12,442	5,728 6,221	358 388.8		384	GDDR6 256-bit	12000		PCIe 4.0 ×16
Radeon Pro 5700 XT (Navi 10)[413][417]				2560:160:64 40 CU	1243 1499	198.9 239.8	79.6 95.94	12,728 15,350	6,364 7,675	397.8 479.7	16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro W5000 series

Main article: Radeon Pro W5000/W5000M series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W5500 (Navi 14)[418][419]	Feb 10, 2020 $399 USD	RDNA TSMC N7	6.4×109 158 mm2	1408:88:32 22 CU	1744 1855	153.4 163.2	55.8 59.36	9,822 10,450	4,911 5,224	306.9 326.5	8	224	GDDR6 128-bit	14000	125 W	PCIe 4.0 ×8	4× DP 1.4a
Radeon Pro W5700 (Navi 10)[420][421]	Nov 19, 2019 $799 USD		10.3×109 251 mm2	2304:144:64 36 CU	1400 1880	201.6 270.7	89.6 120.3	12,902 17,330	6,451 8,663	403.2 541.4		448	GDDR6 256-bit		205 W	PCIe 4.0 ×16	5× miniDP 1.4a 1× USB Type-C

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W5500X (Navi 14)[422][423]	2020	RDNA TSMC N7	6.4×109 158 mm2	1536:96:32 24 CU	1757	163.2	59.36	11,200	5,600	326.5	8	224	GDDR6 128-bit	14000	130 W	PCIe 4.0 ×8	2× HDMI 2.0b
Radeon Pro W5700X (Navi 10)[422][424][423]	Dec 11, 2019		10.3×109 251 mm2	2560:160:64 40 CU	1243 1860	198.8 297.6	79.5 119.04	12,728 19,046	6,364 9,523	397.8 595.2	16	448	GDDR6 256-bit		250 W	PCIe 4.0 ×16	4× Thunderbolt 3 1× HDMI 2.0b

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro W6000 series

Main article: Radeon Pro W6000/W6000M series

Model (Code name)	Release date & price	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Infinity Cache	Memory				TDP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W6300 (Navi 24)[425][426]	Oct 2022 OEM[427]	RDNA 2 TSMC N6	5.4×109 107 mm2	768:48:32:12 12 CU	1512 2040	72.58 97.92	48.38 65.28	4,644 6,267	2,322 3,133	145.1 195.8	8 MB	2	64	GDDR6 32-bit	16000	25 W	PCIe 4.0 ×4	2× DP 1.4a
Radeon Pro W6400 (Navi 24)[428][429]	Jan 19, 2022 $229 USD				2039 2331	97.87 111.9	65.25 74.59	6,264 7,161	3,132 3,580	195.7 223.8	16 MB	4	128	GDDR6 64-bit		50 W
Radeon Pro W6600 (Navi 23)[430][431]	Jun 8, 2021 $649 USD	RDNA 2 TSMC N7	11.06×109 237 mm2	1792:112:64:28 28 CU	2331 2903	261.1 325.1	149.2 185.8	16,709 20,809	8,354 10,404	522.1 650.3	32 MB	8	224	GDDR6 128-bit	14000	130 W	PCIe 4.0 ×8	4× DP 1.4a
Radeon Pro W6800 (Navi 21)[432][433]	Jun 8, 2021 $2249 USD		26.8×109 520 mm2	3840:240:96:60 60 CU	2075 2320	498.0 556.8	199.2 222.7	31,872 35,635	15,936 17,818	996.0 1,114	128 MB	32	512	GDDR6 256-bit	16000	250 W	PCIe 4.0 ×16	6× miniDP 1.4a

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Infinity Cache	Memory				TDP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W6600X (Navi 23)[434][435][436]	Mar 8, 2022	RDNA 2 TSMC N7	11.06×109 237 mm2	2048:124:64:32 32 CU	2068 2479	307.3	158.6	19,673	9,837	614.8	32 MB	8	256	GDDR6 128-bit	16000	120 W	PCIe 4.0 ×8	2× HDMI 2.1
Radeon Pro W6800X (Navi 21)[434][437][438]	Aug 3, 2021		26.8×109 520 mm2	3840:240:96:60 60 CU	1800 2087	432.0 500.8	172.8 200.3	27,648 32,056	13,824 16,028	864.0 1,002	128 MB	32	512	GDDR6 256-bit		300 W	PCIe 4.0 ×16	4× Thunderbolt 3 1× HDMI 2.1
Radeon Pro W6800X Duo (Navi 21)[434][439]			2× 26.8×109 520 mm2	2× 3840:240:96:60 60 CU	1800 1979	2× 432.0 474.9	2× 172.8 189.9	2× 27,648 30,397	2× 13,824 15,199	2× 864.0 949.9		2× 32	2× 512	GDDR6 2× 256-bit		400 W
Radeon Pro W6900X (Navi 21)[434][440]			26.8×109 520 mm2	5120:320:128:80 80 CU	1825 2171	584.0 694.7	233.6 277.8	37,376 44,462	18,688 22,231	1,168 1,389		32	512	GDDR6 256-bit		300 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)

Radeon Pro W7000 series

Main article: Radeon Pro W7000 series

Model (Code name)	Release date & price	Architecture & fab	Chiplets (active)	Transistors & die size[a]	Core		Fillrate[b][c][d]		Processing power[b][e] (TFLOPS)			Infinity Cache	Memory				TDP	Bus interface
					Config[f][g]	Clock[b] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W7500 (Navi 33)[441][442]	Aug 3, 2023 $429 USD	RDNA 3 TSMC N6	—	13.3×109 204 mm2	1792:112:64 28:56:28 CU	1500 1700	168.0 190.4	96.0 108.8	24.37	12.19	0.381	32 MB	8	288	GDDR6 128-bit	18000	70 W	PCIe 4.0 ×8
Radeon Pro W7600 (Navi 33)[441][443]	Aug 3, 2023 $599 USD				2048:128:64 32:64:32 CU	1720 2440	220.1 312.3	110.0 156.2	39.98	19.99	0.625						130 W
Radeon Pro W7700 (Navi 32)	Nov 13, 2023 $999 USD	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 4 × MCD	28.1×109 ~346 mm2	3072:192:96 48:96:48 CU	1900 2600	364.8 499.2	182.4 249.2	56.54	28.3	0.884	64 MB	16	576	GDDR6 256-bit		190 W	PCIe 4.0 ×16
Radeon Pro W7800 (Navi 31)[444][445]	Apr 13, 2023 $2499 USD			57.7×109 ~531 mm2	4480:280:128 70:128:70 CU	1855 2499	519.4 699.7	237.4 319.8	90.50	45.25	1.414		32				260 W
Radeon Pro W7800 48GB (Navi 31)[446]	Dec 2024		1 × GCD 6 × MCD									96 MB	48	864	GDDR6 384-bit		281 W
Radeon Pro W7900 Dual Slot (Navi 31)[447][448]	Jun 19, 2024 $3499 USD				6144:384:192 96:192:96 CU	1855 2495	712.3 958.0	356.1 479.0	122.6	61.32	1.916						295 W
Radeon Pro W7900 (Navi 31)[444][449]	Apr 13, 2023 $3999 USD

• v
• t
• e

1. Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
   Radeon Pro W7800 has only four active MCDs, inactive one is for structural support and heat dissipation.
2. Boost values (if available) are stated below the base value in italic.
3. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
4. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
5. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
6. Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
7. GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

Radeon Pro R9000 series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a]					Infinity Cache	Memory				TBP	Bus interface
								(TFLOPS)[d]			AI TOPS[e]
				Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	INT8	INT4		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon AI Pro R9700 (Navi 48)[450][451][452]	Jul 23, 2025	RDNA 4 TSMC N4P	53.9 billion 357 mm2	4096:256:128 64:128:64 CU	1660 2920	425 747.5	212.5 373.76	54.4 95.68	27.2 47.84	0.425 0.747	217.7 383	435.5 766	64 MB	32	644.6	GDDR6 256-bit	20000	300 W	PCIe 5.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Officially declared performance is twice the one shown here due to the use of sparsity.
6. Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)

Mobile workstation GPUs

Mobility FireGL series

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b]		Processing power[c] (GFLOPS)	Memory				Bus interface	Notes
			Config	Clock (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (MB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)
Mobility FireGL 7800 [453] (M7-GL)	2001-09-29	R100 (150 nm)	0:2:2:2[d]	280	0.56	0.56	Unknown	64	DDR 128-bit	200	6.4	AGP 4x	27 Watt TDP
Mobility FireGL 9000 [454] (M9-GL)	2002-01-01	R200 (150 nm)	1:4:4:4[d]	250	1.0	1.0	Unknown	64	DDR 128-bit	200	6.4	AGP 4x
Mobility FireGL T2 [455] (M10-GL)	2003-11-01	R300 (130 nm)	2:4:4:4[d]	320	1.28	1.28	Unknown	128	DDR 128-bit	200	6.5	AGP 4x
Mobility FireGL T2e [456] (M11-GL)	2004-08-01	R300 (130 nm)	2:4:4:4[d]	450	1.8	1.8	Unknown	128	DDR 128-bit	225	7.2	AGP 4x
Mobility FireGL V3100 [457] (M22-GL)	2004-06-01	R300 (110 nm)	2:4:4:4[d]	350	1.4	1.4	Unknown	128	DDR 128-bit	200	6.4	PCIe 1.0 x16
Mobility FireGL V3200 [458] (M24-GL)	2004-06-01	R300 (130 nm)	2:4:4:4[d]	400	1.6	1.6	Unknown	128	DDR2 128-bit	250	12.8	PCIe 1.0 x16
Mobility FireGL V5000 [459] (M26-GL)	2005-02-03	R420 (110 nm)	6:8:8:8[d]	350	2.8	2.8	Unknown	128	GDDR3 128-bit	425	13.6	PCIe 1.0 x16
Mobility FireGL V5200 [460] (M56-GL)	2006-02-01	R520 (90 nm)	5:12:12:12[d]	425	5.1	5.1	Unknown	256	GDDR3 128-bit	475	15.2	PCIe 1.0 x16
Mobility FireGL V5250 [461] (M66-GL)	2007-01-01	R520 (90 nm)	5:12:12:12[d]	450	5.4	5.4	Unknown	256	GDDR3 128-bit	350	11.2	PCIe 1.0 x16
Mobility FireGL V5600 [462] (M76-GL)	2007-05-14	TeraScale 1 (65 nm)	120:8:4[e]	500	4.0	2.0	120.0	256	GDDR3 128-bit	400	12.8	PCIe 2.0 x16
Mobility FireGL V5700 [463] (M86-GL)	2008-01-07	Terascale 2 (55 nm)	120:8:4[e]	600	4.8	2.4	144	512	GDDR3 128-bit	700	22.4	PCIe 2.0 x16	in Lenovo ThinkPad W500
Mobility FireGL V5725 [464] (M86-GL)	2009-01-01	Terascale 2 (55 nm)	120:8:4[e]	680	5.44	2.72	163.2	256	GDDR3 128-bit	800	25.6	PCIe 2.0 x16

• v
• t
• e

1. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
2. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
4. Vertex shader : Pixel shaders: Texture Mapping Units : Render Output Units
5. Unified Shaders : Texture Mapping Units : Render Output Units

FirePro Mobile series

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b]		Processing power[c] (GFLOPS)	Memory				Bus interface	Notes
			Config[d] (CU)	Clock (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (MB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)
FirePro M5725 [465] (M96 GL)	2009-01-01	Terascale 2 (55 nm)	320:32:8 (3)	680	21.6	5.4	432	256	GDDR3 128-bit	800	25.6	PCIe 2.0 x16
FirePro M5800 [466] (Madison XT GL)	2010-03-01	Terascale 2 (40 nm)	400:20:8 (5)	650	13	5.2	520	1024	GDDR5 128-bit	800	25.6	PCIe 2.0 x16	HP EliteBook 8540w
FirePro M3900 [467] (Seymour XT)	2011-04-13		160:8:4 (2)	700	6.0	3.0	224	1024	DDR3 64-bit	900	14.4	PCIe 2.1 x16	HP Elitebook 8460w
FirePro M5950 [468] (Whistler XT)	2011-01-04		480:24:8 (6)	725	17.4	5.8	696	1024	GDDR5 128-bit	900	57.6	PCIe 2.1 x16	Dell Precision M4600, HP EliteBook 8560w
FirePro M7740 [469] (M97XT GL)	2009-08-04	Terascale 1 (40 nm)	640:32:16 (8)	650	20.8	10.4	832	1024	GDDR5 128-bit	1000	64	PCIe 2.0 x16	Dell Precision M6400 and M6500
FirePro M7820 [470] (Juniper XT)	2010-05-01	Terascale 2 (40 nm)	800:40:16 (10)	700	28	11.2	1120	1024	GDDR5 128-bit	1000	64	PCIe 2.0 x16	Dell Precision M6500, HP EliteBook 8740w
FirePro M8900 [471] (Blackcomb XT GL)	2011-04-12		960:48:32 (12)	680	32.64	21.76	1310	2048	GDDR5 256-bit	900	115.2	PCIe 2.1 x16	Dell Precision M6600
FirePro M2000 [472] (Turks GL)	2012-07-01		480:24:8 (6)	500	12	4	480	1024	GDDR5 64-bit	800	25.6	PCIe 2.1 x16	HP EliteBook 8470w
FirePro M4000 [473] (Chelsea XT GL)	2012-06-27	GCN 1st gen (28 nm)	512:32:16 (8)	600	19.2	9.6	614	2048	GDDR5 128-bit	1000	51.2	PCIe 2.1 x16	HP EliteBook 8570w, HP EliteBook 8770w, Dell Precision M4700 (e.g. Consumer HD7700M Serie DevID 682D)
FirePro M6000 [474] (Heathrow XT GL)	2012-06-27		640:40:16 (10)	800	30	12	960	2048	GDDR5 128-bit	1000	64	PCIe 3.0 x16	Dell Precision M6700
FirePro M4100 [475] (Mars)	2013-10-16		384:24:8 (6)	670	16.1	5.4	514	2048	GDDR5 128-bit	1000	64	PCIe 3.0 x16	HP ZBook 14
FirePro W4170M [476] (Mars XTX)	2014-04-28		384:24:8 (6)	825	19.8	6.6	691.2	2048	GDDR5 128-bit	1125	72	PCIe 3.0 x16	Dell Precision M2800, HP ZBook 15u G2
FirePro W4190M [477] (Opal)	2015-11-12		384:24:8 (6)	825	19.8	6.6	634	2048	GDDR5 128-bit	900	72	PCIe 3.0 x16	HP ZBook 15u G3, MXM-3-A, OpenGL 4.6, OpenCL 2.0, TDP 25W [478]
FirePro M5100 [479] (Venus XT)	2013-10-16		640:40:16 (10)	775	31	12.4	992	2048	GDDR5 128-bit	1125	72	PCIe 3.0 x16	Dell Precision M4800, Panasonic Toughbook 54, HP ZBook 15 G2 (e.g. R9 M200X Serie DevID 6821)
FirePro W5130M [480] (Tropo LE)	2015-10-02		512:32:16 (8)	up to 925	28.8	14.4	up to 950	up to 2048	GDDR5 128-bit	1000	64	PCIe 3.0 x16	Dell Precision 3510 (e.g. Consumer R7 M465X DevID 682B) MXM-3-A, DirectX 12.0 (feature level 11_1), OpenGL 4.6, OpenCL 2.0, Vulkan 1.0, TDP 35W [481]
FirePro W5170M [482] (Tropo XT)	2014-08-25		640:40:16 (10)	up to 925	36.0	14.4	up to 1180	up to 2048	GDDR5 128-bit	1125	72	PCIe 3.0 x16	Dell Precision 7510, Dell Precision 7710, HP ZBook 15 G3 (e.g. Consumer R9 M375X DevID 6820 REV 083) MXM-3-A, DirectX 12.0 (feature level 11_1), OpenGL 4.6, OpenCL 2.0, Vulkan 1.0, TDP 45W [483]
FirePro M6100 [484] (Saturn XT GL)	2013-10-16	GCN 2nd gen (28 nm)	768: 48:16 (12)	up to 1100	51.6	17.2	1651.2	2048	GDDR5 128-bit	1375/1500	88/96	PCIe 3.0 x16	Dell Precision M6600 / M6800, HP Zbook 17 G2
FirePro W6150M [485] (Saturn XT GL)	2015-11-12		768:48:16 (12)	1075	51.6	17.2	1651	4096	GDDR5 128-bit	1375	88	PCIe 3.0 x16	HP Zbook 17 G3, MXM-3-B, OpenGL 4.6, OpenCL 2.0, TDP 100W [486]
FirePro W6170M [487] (Saturn XT GL)	2014-08-25		768:48:16 (12)	1075	51.6	17.2	1651	4096	GDDR5 128-bit	1375	88	PCIe 3.0 x16	HP ZBook 17 G2
FirePro W7170M [488] (Amethyst XT)	2015-10-02	GCN 3rd gen (28 nm)	2048:128:32 (32)	723	92.5	23.1	2960	4096	GDDR5 256-bit	1250	160	PCIe 3.0 x16	Dell Precision 7710, MXM-3-B, DirectX 12.0 (feature level 11_1), OpenGL 4.6, OpenCL 2.0, Vulkan 1.0, TDP 100W [489]

• v
• t
• e

1. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
2. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
4. Unified Shaders : Texture Mapping Units : Render Output Units

Radeon Pro WX x100 Mobile series

Main article: AMD Radeon Pro

• Half precision power (FP16) is equal to single precision power (FP32) in 4th GCN generation (in 5th Gen: half precision (FP16) = 2× SP (FP32))

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro WX 2100 (Mobile) (Polaris 12)[490][491][492]	Mar 1, 2017	GCN 4 Samsung/GloFo 14LPP[493]	2.2×109 103 mm2	512:32:16 8 CU	925 1219	29.60 39.01	14.80 19.50	947.2 1,250	59.20 78.02	2	48	GDDR5 64-bit	6000	35 W	PCIe 3.0 ×16
Radeon Pro WX 3100 (Mobile) (Polaris 12)[494][495][496]										4	96	GDDR5 128-bit		50 W
Radeon Pro WX 4130 (Mobile) (Polaris 11)[497][498]			3.0×109 123 mm2	640:40:16 10 CU	1002 1053	40.08 42.12	16.03 16.85	1,282 1,348	80.16 84.24					50 W
Radeon Pro WX 4150 (Mobile) (Polaris 11)[499][500]				896:56:16 14 CU	1002 1053	56.11 58.97	16.03 16.85	1,796 1,887	112.2 117.9					45-50 W
Radeon Pro WX 4170 (Mobile) (Polaris 11)[501][502]				1024:64:16 16 CU	1002 1201	64.12 76.86	16.03 19.22	2,052 2,460	128.3 153.7		112			50-60 W
Radeon Pro WX 7100 (Mobile) (Polaris 10)[503][504]			5.7×109 232 mm2	2304:144:32 36 CU	1188 1243	171.1 179.0	38.0 39.78	5,474 5,728	342.1 358.0	8	160	GDDR5 256-bit	5000	100-130 W
Radeon Pro WX 7130 (Mobile) (Polaris 10)[505][506]

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units (TMUs) multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units (ROPs) multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro 400 series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro 450 (Polaris 11)[507][508][509][510][511][512]	Oct 30, 2016	GCN 4 GloFo 14 nm	3.0×109 123 mm2	640:40:16 10 CU	800	32.00	12.80	1,024	1,024	64.00	2	80	GDDR5 128-bit	5000	35 W	PCIe 3.0 ×8
Radeon Pro 455 (Polaris 11)[507][508][509][513][514]				768:48:16 12 CU	855	41.04	13.68	1,313	1,313	82.08
Radeon Pro 460 (Polaris 11)[507][508][509][515][516]				1024:64:16 16 CU	850 907	54.40 58.05	13.60 14.51	1,741 1,858	1,741 1,858	108.8 116.1	4

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro 500 series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro 555 (Polaris 21)[517][518][519][520]	Jun 6, 2017	GCN 4 GloFo 14 nm	3.0×109 123 mm2	768:48:16 12 CU	850	40.80	13.60	1,306	1,306	81.60	2	81.60	GDDR5 128-bit	5100	50 W	PCIe 3.0 ×16
Radeon Pro 555X (Polaris 21)[517][518][519][521]	Jul 16, 2018				907	43.54	14.51	1,393	1,393	87.07	4	94.08		5900	50 W
Radeon Pro 560 (Polaris 21)[517][518][519][522]	Jun 6, 2017			1024:64:16 16 CU	907	58.05	14.51	1,858	1,858	116.1		81.28		5100	50 W
Radeon Pro 560X (Polaris 21)[517][518][519][523]	Jul 16, 2018				1004	64.26	16.06	2,056	2,056	128.5		94.08		5900	75 W
Radeon Pro 570 (Polaris 20)[517][518][519][524]	Jun 6, 2017		5.7×109 232 mm2	1792:112:32 28 CU	1000 1105	112.0 123.8	32.00 35.36	3,584 3,960	3,584 3,960	224.0 247.5		217.0	GDDR5 256-bit	6800	120 W
Radeon Pro 570X (Polaris 20)[525][526]	Mar 18, 2019											217.6			150 W
Radeon Pro 575 (Polaris 20)[517][518][519][527]	Jun 6, 2017			2048:128:32 32 CU	1096	140.3	35.07	4,489	4,489	280.6		217.0			120 W
Radeon Pro 575X (Polaris 20)[525][528]	Mar 18, 2019											217.6			150 W
Radeon Pro 580 (Polaris 10)[517][518][519][529]	Jun 6, 2017			2304:144:32 36 CU	1100 1200	158.4 172.8	35.2 38.4	5,069 5,530	5,069 5,530	316.8 345.6	8	217.0			150 W
Radeon Pro 580X (Polaris 10)[525][530]	Mar 18, 2019											218.9			185 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro WX x200 Mobile series

Model (Codename)	Release date	Architecture & Fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Bus type & width	Size (GB)	Clock (MT/s)	Bandwidth (GB/s)
Radeon Pro WX 3200 (Mobile)[531][532] (Polaris 23 XT GLM)	March 1, 2017	GCN 4th gen GloFo 14 nm	2.2×109 103 mm2	640:32:16 10 CU	1082 1295 ?	34.62 41.44 ?	17.31 20.72 ?	1,385 1,658	86.56 103.6	GDDR5 128-bit	4	4000	64	65 W	PCIe 3.0 ×8

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified Shaders : Texture Mapping Units : Render Output Units : Compute Units

Radeon Pro Vega series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro Vega 16 (Vega 12)[533][534][535]	Nov 14, 2018	GCN 5 GloFo 14 nm	?	1024:64:32 16 CU	815 1190	52.16 76.16	26.08 38.08	3,338 4,874	1,669 2,437	104.3 152.3	4	307.2	HBM2 1024-bit	2400	50 W	PCIe 3.0 ×16
Radeon Pro Vega 20 (Vega 12)[533][534][536]				1280:80:32 20 CU	815 1283	65.20 102.6	26.08 41.06	4,173 6,569	2,086 3,285	130.4 205.3		189.4		1480	50 W
Radeon Pro Vega 48 (Vega 10)[537][538]	Mar 19, 2019		12.5×109 495 mm2	3072:192:64 48 CU	1200	230.4	76.80	14,746	7,373	460.8	8	402.4	HBM2 2048-bit	1572	?
Radeon Pro Vega 56 (Vega 10)[539][540][541]	Aug 17, 2017			3584:224:64 56 CU	1138 1250	254.9 280.0	72.83 80.00	16,314 17,920	8,157 8,960	509.8 560.0					120 W
Radeon Pro Vega 64 (Vega 10)[539][540][542]	Jun 17, 2017			4096:256:64 64 CU	1250 1350	320.0 345.6	80.00 86.40	20,480 22,118	10,240 11,059	640.0 691.2	16				?
Radeon Pro Vega 64X (Vega 10)[539][543]	Mar 19, 2019			4096:256:64 64 CU	1250 1468	320.0 375.8	80.00 93.95	20,480 24,051	10,240 12,026	640.0 751.6		512.0		2000

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro 5000M series

Model (Code name)	Release date	Architecture & fab	Transistors  die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro 5300M (Navi 14)[544][545]	Nov 13, 2019	RDNA TSMC N7	6.4×109 158 mm2	1280:80:32 20 CU	1000 1250	80.00 100.0	32.00 40.00	5,120 6,400	2,560 3,200	160.0 200.0	4	192	GDDR6 128-bit	12000	50 W	PCIe 4.0 ×8
Radeon Pro 5500M (Navi 14)[544][546]				1536:96:32 24 CU	1000 1300	96.00 124.8	32.00 41.60	6,144 8,908	3,072 4,454	192.0 278.4	4 8
Radeon Pro 5600M (Navi 12)[544][547]	Jun 15, 2020		Unknown	2560:160:64 40 CU	1000 1035	160.0 165.6	64.00 66.24	10,240 10,598	5,120 5,299	320.0 331.2	8	394	HBM2 2048-bit	1540		PCIe 4.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro W5000M series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W5500M (Navi 14)[548][549]	Feb 10, 2020	RDNA TSMC N7	6.4×109 158 mm2	1408:88:32 22 CU	1000 1700	88.00 149.6	32.00 54.40	5,632 9,574	2,816 4,787	176.0 299.2	4	224	GDDR6 128-bit	14000	65-85 W	PCIe 4.0 ×8

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon Pro W6000M series

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			Infinity Cache	Memory				TDP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro W6300M (Navi 24)[550][551]	Jan 19, 2022	RDNA 2 TSMC N6	5.4×109 107 mm2	768:48:32:12 12 CU	2214	106.3	70.8	6,801	3,401	212.5	8 MB	2	64	GDDR6 32-bit	14000	25 W	PCIe 4.0 ×4
Radeon Pro W6500M (Navi 24)[552][553]				1024:64:32:16 16 CU	2588	165.6	82.8	10,478	5,239	327.4	16 MB	4	128	GDDR6 64-bit		35–50 W
Radeon Pro W6600M (Navi 23)[554][555][556]	Jun 8, 2021	RDNA 2 TSMC N7	11.06×109 237 mm2	1792:112:64:28 28 CU	2200 2900	246.4 324.8	140.8 185.6	15,770 20,787	7,885 10,394	492.8 649.6	32 MB	8	224	GDDR6 128-bit		65–90 W	PCIe 4.0 ×16

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)

Server GPUs

FireStream series

Main article: AMD FireStream

Model (Codename)	Launch	Architecture (Fab)	Bus interface	Stream processors	Clock rate		Memory				Processing power[a] (GFLOPS)		TDP (Watts)
					Core (MHz)	Memory (MHz)	Size (MB)	Type	Bus width (bit)	Bandwidth (GB/s)	Single	Double
Stream Processor (R580)	2006	R500 80 nm		240	600		1024	GDDR3	256	83.2	375[557]	N/A	165
FireStream 9170 (RV670)[558][559]	November 8, 2007	TeraScale 1 55 nm	PCIe 2.0 x16	320	800	800	2048	GDDR3	256	51.2	512	102.4	105
FireStream 9250 (RV770)[560][561]	June 16, 2008	TeraScale 1 55 nm	PCIe 2.0 x16	800	625	993	1024	GDDR3	256	63.6	1000	200	150
FireStream 9270 (RV770)[562][563]	November 13, 2008	TeraScale 1 55 nm	PCIe 2.0 x16	800	750	850	2048	GDDR5	256	108.8	1200	240	160
FireStream 9350 (Cypress XT)[564]	June 23, 2010	TeraScale 2 40 nm	PCIe 2.1 x16	1440	700	1000	2048	GDDR5	256	128	2016	403.2	150
FireStream 9370 (Cypress XT)[565]	June 23, 2010	TeraScale 2 40 nm	PCIe 2.1 x16	1600	825	1150	4096	GDDR5	256	147.2	2640	528	225

• v
• t
• e

1. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

FirePro Remote series

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)			TDP (Watts)	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL
FirePro RG220[566]	May 2010	RV711	55	PCIe 2.0 ×16	500	800	80(16×5):8:4:1	2.0	4.0	512	12.8	GDDR3 for GPU, RDRAM for PCoIP	64	80	No	10.1	3.3	1.0	35	Dual Ethernet ports plus DMS-59 for dual DVI-D output (no VGA host output)
FirePro R5000[567]	February 25, 2013	Pitcairn LE GL (GCN 1st gen)	28	PCIe 3.0 ×16	825		768:48:32:12	26.4	39.6	2048	102.4	GDDR5	256	1267.2	79.2	11.1	4.5	1.2	<150	Ethernet port plus 2× Mini DisplayPort with Tera2 PCoIP

¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

FirePro Server series (S000x/Sxx 000)

• Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher.^[344] OpenGL 4.5 was only in Windows available.^[345] Actual Linux Driver support OpenGL 4.5 and Vulkan 1.0, but only OpenCL 1.2 by AMDGPU Driver 16.60.^[358]
• Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs.^[346]

Model	Launch	Microarchitecture	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	DirectX	OpenGL	OpenCL	Vulkan
FirePro S4000x[568][569]	August 7, 2014	GCN 1st gen	Venus XT	28	PCIe 3.0 x16	950	1200	640:40:16:10	11.6	29	2	72	GDDR5	256	992	62	11.1 12.0	4.5	1.2	1.0	<45	Type A MXM form factor, no physical display outputs
FirePro S7000[570]	August 27, 2012		Pitcairn XT			950		1280:80:32:20	30.4	76	4	153.6			2432	152					<150	1× DP
FirePro S7100X[571][572][573][574]	May 25, 2016	GCN 3rd gen	Amethyst XT			723	1050	2048:128:32:32	23.14	92.5	8	160			2961	TBA	11.2 12.0		2.0	1.1	100	For blade servers, MXM Module 3.1
FirePro S7150[575][576][577][578]	February 1, 2016		Tonga PRO GL			1050	1250	1792:112:32:28	33.6	117.6					3763	250					150	ECC RAM, two Slots
FirePro S7150 X2[575][577][579][580]			2× Tonga PRO GL					2× 1792:112:32:28			16	2× 160			7540	500					265	ECC RAM, no physical display outputs
FirePro S9000[581]	August 27, 2012	GCN 1st gen	Tahiti PRO GL			900	1375	1792:112:32:28	28.8	100.8	6	264		384	3225.6	806.4	11.1 12.0		1.2	1.0	<225	ECC RAM, 1× DisplayPort
FirePro S9050[582][583]	August 6, 2014										12
FirePro S9100[584]	October 2, 2014	GCN 2nd gen	Hawaii Pro GL			824	1250	2560:160:64:40	52.74	131.8		320		512	4219	2109			2.0			ECC RAM, no physical display outputs
FirePro S9150[585][586][587]	August 6, 2014		Hawaii XT GL			900		2816:176:64:44	57.6	158.4	16				5070	2530	11.2 12.0				<235
FirePro S9170[588][589]	July 8, 2015		Grenada XT GL			930	1375		59.52	163.68	32				5240	2620					<275	ECC RAM, full throughput double precision, no physical display outputs
FirePro S9300 x2[590][591][592][593][594]	March 31, 2016	GCN 3rd gen	2× Capsaicin XT			850	2× 500	2× 4096:256:64:64	54.4	217.6	2× 4	2× 512	HBM	2× 4096	13900	868				1.1	300	Non-ECC RAM, half-precision (FP16) support, no physical display outputs
FirePro S10000[595]	November 12, 2012	GCN 1st gen	2× Zaphod (Tahiti Pro GL)			825	1250	2× 1792:112:32:28	52.8	184.8	2× 3	2× 240	GDDR5	384	5913.6	1478.4	11.1 12.0		1.2	1.0	<375	ECC RAM, 4x DP, 1x DVI-I
FirePro S10000 passive[596]			2× Tahiti PRO GL																			ECC RAM, 1x Mini DP, 1x DVI-I

¹ Unified shaders : Texture mapping units : Render output units: Compute units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs^[353]

Radeon Sky series

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (GiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision	Double precision	Direct3D	OpenGL	OpenCL	Vulkan
Radeon Sky 500[597]	April 2013	Pitcairn XT	28	PCIe 3.0 x16	950	1200	1280:80:32:20	30.4	76	4	153.6	GDDR5	256	2432	152	12.0	4.5	1.2	?	150	One DisplayPort
Radeon Sky 700[598]		Tahiti PRO			900	1375	1792:112:32:28	28.8	100.8	6	264		384	3225.6	806.4					225
Radeon Sky 900[599]		2× Tahiti PRO			825 950	1250	2× 1792:112:32:28	52.8	184.8	2× 3	2× 240		2x 384	5913.6	1478.4					300	4× Mini DisplayPort, 1× DVI-I

¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

Radeon Pro V series

Main article: Radeon Pro

Model (Code name)	Release date	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)			L3 cache	Memory				TDP	Bus interface	Graphic output ports
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double		Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)
Radeon Pro V320 (Vega 10)[600][601][602]	Jun 29, 2017 (Custom SKU)	GCN 5 GF 14LPP	12.5×109 495 mm2	4096:256:64:- 64 CU	852 1000	218.1 256	54.52 64	13,959 16,384	6,979 8,192	436.2 512	—	8 or 16	484	HBM2 2048-bit	1890	230 W	PCIe 3.0 ×16	4× miniDP 1.4a
Radeon Pro V340 (Vega 10)[603][604][605][606]	Aug 26, 2018		2× 12.5×109 495 mm2	2× 3584:224:64:- 56 CU	852 1500	2× 190.8 336	2× 54.52 96	2× 12,214 21,504	2× 6,107 10,752	2× 381.7 672		2× 16	2× 484	HBM2 2× 2048-bit		300 W		1× miniDP 1.4a
Radeon Pro V520 (Navi 12)[607][608]	Dec 1, 2020	RDNA TSMC N7	Unknown	2304:144:64:- 36 CU	1000 1600	144 230.4	64 102.4	9,216 14,746	4,608 7,373	288 460.8		8	512	HBM2 2048-bit	2000	225 W	PCIe 4.0 ×16	—
Radeon Pro V620 (Navi 21)[609][610]	Nov 4, 2021	RDNA 2 TSMC N7	26.8×109 520 mm2	4608:288:128:72 72 CU	1825 2200	525.6 633.6	233.6 281.6	33,638 40,550	16,819 20,275	1,051 1,267	128 MB	32		GDDR6 256-bit	16000	300 W
Radeon Pro V710 (Navi 32)[611][612]	Oct 3, 2024	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	28.1×109 384 mm2	3456:216:96:54 54 CU	1900 2000	432	192	55,296	28,314	1,728	54 MB	28	448	GDDR6 224-bit	16000	158 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)

Radeon Instinct series

Main article: AMD Instinct accelerators

Model (Code name)	Launch	Architecture & fab	Transistors & die size	Core		Fillrate[a][b][c]		Processing power[a][d] (TFLOPS)			Memory				TBP	Bus interface
				Config[e]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (GB)	Bus type & width	Bandwidth (GB/s)	Clock (MT/s)
Radeon Instinct MI6 (Polaris 10)[613][614][615][616][617][618]	Jun 20, 2017	GCN 4 GloFo 14LP	5.7×109 232 mm2	2304:144:32 36 CU	1120 1233	161.3 177.6	35.84 39.46	5.161 5.682	5.161 5.682	0.323 0.355	16	GDDR5 256-bit	224	7000	150 W	PCIe 3.0 ×16
Radeon Instinct MI8 (Fiji)[613][614][615][619][620][621]		GCN 3 TSMC 28 nm	8.9×109 596 mm2	4096:256:64 64 CU	1000	256.0	64.00	8.192	8.192	0.512	4	HBM 4096-bit	512	1000	175 W
Radeon Instinct MI25 (Vega 10)[613][614][615][622][623][624][625]		GCN 5 GloFo 14LP	12.5×109 510 mm2		1400 1500	358.4 384.0	89.60 96.00	22.94 24.58	11.47 12.29	0.717 0.768	16	HBM2 2048-bit	484	1890	300 W
Radeon Instinct MI50 (Vega 20)[626][627][628][629][630][631]	Nov 18, 2018	GCN 5 TSMC N7	13.2×109 331 mm2	3840:240:64 60 CU	1450 1725	348.0 414.0	92.80 110.4	22.27 26.50	11.14 13.25	5.568 6.624	16 32	HBM2 4096-bit	1024	2000		PCIe 4.0 ×16
Radeon Instinct MI60 (Vega 20)[627][632][633][634]				4096:256:64 64 CU	1500 1800	384.0 460.8	96.00 115.2	24.58 29.49	12.29 14.75	6.144 7.373	32
AMD Instinct MI100 (Arcturus)[635][636][637]	Nov 16, 2020	CDNA TSMC N7	25.6×109 750 mm2	7680:480:- 120 CU	1000 1502	480.0 721.0	—	122.9 184.6	15.36 23.07	7.680 11.54			1228.8	2400
AMD Instinct MI210 (Aldebaran)[638][639][640]	Mar 22, 2022	CDNA 2 TSMC N6	28 x 109 ~770 mm2	6656:416:- 104 CU (1 × GCD)[f]	1000 1700	416.0 707.2		106.5 181.0	13.31 22.63	13.31 22.63	64	HBM2E 4096-bit	1638.4	3200
AMD Instinct MI250 (Aldebaran)[641][642][643]	Nov 8, 2021		58 x 109 1540 mm2	13312:832:- 208 CU (2 × GCD)		832.0 1414		213.0 362.1	26.62 45.26	26.62 45.26	2 × 64	HBM2E 2 × 4096-bit[g]	2 × 1638.4		500 W 560 W (Peak)
AMD Instinct MI250X (Aldebaran)[644][642][645]				14080:880:- 220 CU (2 × GCD)		880.0 1496		225.3 383.0	28.16 47.87	28.16 47.87
AMD Instinct MI300A (Antares)[646][647][648][649]	Dec 6, 2023	CDNA 3 TSMC N5 & N6	146 x 109 1017 mm2	14592:912:- 228 CU (6 × XCD) (24 AMD Zen 4 x86 CPU cores)	2100	912.0 1550.4		980.6 1961.2 (With Sparsity)	122.6	61.3 122.6 (FP64 Matrix)	128	HBM3 8192-bit	5300	5200	550 W 760 W (Liquid Cooling)	PCIe 5.0 ×16
AMD Instinct MI300X (Aqua Vanjaram)[650][651][652][653]			153 x 109 1017 mm2	19456:1216:- 304 CU (8 × XCD)		1216.0 2062.1		1307.4 2614.9 (With Sparsity)	163.4	81.7 163.4 (FP64 Matrix)	192				750 W

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of texture mapping units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of render output units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Unified shaders : Texture mapping units : Render output units and Compute units (CU)
6. GCD Refers to a Graphics Compute Die. Each GCD is a different piece of silicon.
7. CDNA 2.0 Based cards adopt a design using two dies on the same package.They are linked with 400GB/s Bidirectional Infinity Fabric link, The dies are addressed as individual GPUs by the host system.

Embedded GPUs

Model (Code name)	Launch	Architecture & fab	Bus interface	Clock rate		Core config1,2	Fillrate		Memory				Processing power (GFLOPS)		API compliance (version)				TDP (Watts)	Notes
				Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size	Bandwidth (GB/s)	Type	Bus width (bit)	Single	Double	Direct3D	OpenGL	OpenCL	Vulkan
Radeon E2400[654][655][656] (RV610)[657][658]	Jun 2007	Terascale 1 TSMC 65 nm	PCIe 1.1 ×16	600	700	40:4:4	2.40	2.40	128 MB 256 MB	11.2	GDDR3	64	48	—	10.0	3.3	—	—	7-13	Form factor: PCIe or MXM-II 2× DVI
Radeon E4690[659][660] (RV730)[661][662][663]	Jun 2009	Terascale 1 TSMC 55 nm	PCIe 2.0 ×16			320:32:8	4.80	19.20	512 MB	22.4		128	384		10.1		1.0		8-25	Form factor: PCIe or MXM (MXM-II or MXM 3.0 Type A) 2× DVI
Radeon E6460[664][665] (Caicos)[666]	Apr 2011	Terascale 2 TSMC 40 nm	PCIe 2.1 ×16		800	160:8:4:2	2.40	4.80		25.6	GDDR5	64	192		11.2	4.1 (up to 4.4)	1.1 (1.2)		19-21	PCIe (4× miniDP/DVI or 2× DVI and DP)
Radeon E6465[667] (Caicos)[668]	Sep 2015								2 GB										20	PCIe (4× miniDP or 2× DP), or MXM Type A (4× DP/HDMI/DVI)
Radeon E6760[669] (Turks)	May 2011					480:24:8:6	4.80	14.40	1 GB	51.2		128	576						37-42
Radeon E8860[670] (Venus)	Jan 2014	GCN 1 TSMC 28 nm	PCIe 3.0 ×16	625	1125	640:40:16 10 CU	10.00	25.00	2 GB	72		128	768?	48?	12.0	4.5 (4.6)	1.2 (2.1)	1.0 (1.2)	37	PCIe, MXM Type A, or MCM; with or w/o fan; miniDP, DVI+miniDP, or DP/HDMI/DVI
Radeon E8870[670] (Saturn)	Sep 2015	GCN 2 TSMC 28 nm		1000	1500	768:48:16 12 CU	16.00	48.00	4 GB	96			1536	96.00			2.0 (2.1)		75	PCIe (4× DP) or MXM Type B (6× DP/HDMI/DVI)
Radeon E8950 (Amethyst)[671]	Sep 2015	GCN 3 TSMC 28 nm	MXM-B 3.0	735	1500	2048:128:32 32 CU	23.52	94.08	8 GB	192		256	3011	188.16					95	Form factor: MXM Type B 3.0
Radeon E9171[667] (Polaris12)	Oct 2017	GCN 4 GloFo 14 nm	PCIe 3.0 ×8	1124 or 1219	1500	512:32:16 8 CU	17.98 19.50	35.97 39.01	4 GB	96		128	1150 1248	71.94 78.02					35	5× miniDP or 2× miniDP+DP (PCIe); 5× DP/HDMI/DVI (on MXM Type A and MCM)
Radeon E9172[667] (Polaris12)									2 GB	48		64
Radeon E9173[667][672] (Polaris12)
Radeon E9174[667] (Polaris12)									4 GB	96		128							50
Radeon E9175[667] (Polaris12)
Radeon E9260[670] (Polaris11)	Sep 2016				1750	896:48:16 14 CU				112			2500						50-80	PCIe (4× miniDP) or MXM Type A (5× DP/HDMI/DVI)
Radeon E9390[673] (Polaris10)	Oct 2019		PCIe 3.0 ×16	1086	1250	1792:112:32 28 CU			8 GB	160		256	3892	243.26					75	4× DisplayPort
Radeon E9550[673] (Polaris10)	Sep 2016			1243		2304:144:32 36 CU							5728	357.98					95	MXM Type B 6× DP/HDMI
Radeon E9560[673] (Polaris10)	Oct 2019				1750					224									130	4× DisplayPort
Radeon E9565[673] (Polaris10)	Sep 2020								16 GB										135	6× miniDP

¹ Unified shaders : Texture mapping units : Render output units
² CU = Compute units
³ The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

Console GPUs

Code name (console model)	Launch	GPU code name and/or architecture	Fab (nm)	Transistors (million)	Core config1,2,3	Core clock (MHz)	Fillrate				Ray-tracing performance		ML Performance		Memory					Bus interface	API compliance (version)			Processing power (GFLOPS)	Architecture features
							MOperations/s	MPixels/s	MTexels/s	MTri/s	GRays/s (triangles)	GRays/s (voxels or boxes)	TOPS (INT8)	TOPS (INT4)	Size (MiB)	Clock (MHz)	RAM type	Bus width (bit)	Bandwidth (GB/s)		Direct3D	OpenGL	Other
Project Dolphin (GameCube) [674][675][676][677][678]	September 14, 2001	Flipper	NEC 180 nm[679]	51[680] (GPU + eDRAM)	4:1:4:4	162	7,500	648	648	60	-	-	-	-	24 internal 16 shared 3 eDRAM	324 81 162	1T-SRAM SDRAM eDRAM	64 8 384/512	3.2 1.6 7.8/10.4	Integrated	No	Unknown	GX	7.5	Fixed-function T&L, TEV register combiner
Xenon (Xbox 360)	November 22, 2005	Xenos GPU TeraScale (HD 2000/3000 based)	TSMC 90 nm 65 nm 45 nm	232[681] (GPU) 105 (eDRAM)[682]	240:16:8 eDRAM (192 parallel pixel processors)	500	240,000	4000 eDRAM (16000 with 4x MSAA)	8000	500	-	-	-	-	512 (shared) 10 eDRAM	700 500	GDDR3 eDRAM	128	22.4 32 (GPU to daughter die) 256 (Daughter die ROP to eDRAM)		9.0c+	No	Unknown	240	Surface tessellation
Revolution (Wii)	November 19, 2006	Hollywood	NEC 90 nm	107[683] (GPU + eDRAM)	4:1:4:4	243	11,250	972	972	70	-	-	-	-	24 internal 64 shared 3 eDRAM	486 486 243	1T-SRAM GDDR3 eDRAM	64 64 384/512	3.88 3.88 11.2/15.6		No	Unknown	GX	11.25	Fixed-function T&L, TEV register combiner
Project Café (Wii U)	November 18, 2012	Latte4 GPU TeraScale (HD 4000 based)	Renesas 45 nm	880[684] GPU + eDRAM	160:16:8	550	176,000	4400	8800	550	-	-	-	-	2048 (shared) 32 eDRAM, 1024-bit wide	800 (1600 effective) 550	DDR3 eDRAM	64 1024	12.8 70.4		No	Unknown	GX2	176	Fixed-function T&L, TEV register combiner, Interpolation Units for TMU assist
Durango (Xbox One)[685]	November 22, 2013	GCN 2	TSMC 28 nm (One S) 16 nm	4,800[686] GPU + eSRAM GPU probably ~2,000	768:48:16	853, (One S) 914	1,310,208, (One S) 1,403,904	13,648, (One S) 14,624	40,944, (One S) 43,872	1300	-	-	-	-	8192 (shared) 32 eSRAM	1066.5 (2133 effective) 1706 (3412 effective)	DDR3 eSRAM		68.3 218, 219 (One S)		11.2[687] 12	No	Mantle technically possible	1310.2, (One S) 1403.9	Tiled resources, (One S) Upscaled 4K HDR support
Liverpool (PlayStation 4)[688]	November 15, 2013		TSMC 28 nm 16 nm	probably ~2,800	1152:72:32	800	1,843,200	25,600	57,600	1707	-	-	-	-	8192 (shared)	1375 (5500 effective)	GDDR5	256	176		No	4.2	GNM, GNMX, PlayStation Shader Language, Mantle technically possible	1843.2	HDR possible (only 2K)
Neo (PlayStation 4 Pro)[689][690][691]	November 10, 2016	GCN 4	TSMC 16 nm	5,700	2304:144:32	911	4,197,888	29,152	131,200	3078	-	-	-	-		1700 (6800 effective)			217.6		No	4.2 (4.5)		4197.8	4K HDR possible, fully compatible PS4 mode with reduced power consumption
Scorpio Engine (Xbox One X)[692][693]	November 7, 2017			6,600[686]	2560:160:32	1172	6,000,640	37,504	187,520	4400	-	-	-	-	12288 (shared)			384	326.4		11.2 12	No	Unknown	6000.6	4K HDR support, supersampling
Lockhart (Xbox Series S)	November 10, 2020	RDNA 2	TSMC 7 nm / 6 nm	5,900	1280:80:32:20	1565	FP32: 4,006,400 FP16: 8,012,800	50,080	125,200	2400	-	-	-	-	8192 (GPU) + 2048 (shared)	1750 (14000 effective)	GDDR6	128	224		12U	No	Vulkan 1.3	FP32: 4006 FP16: 8013	DirectX raytracing, FidelityFX Super Resolution - FSR, FSR 2, FSR 3, DirectML, 4K HDR support, variable refresh rate, 120 Hz support
Anaconda (Xbox Series X)[686]				15,300	3328:208:64:52	1825	FP32: 12,147,200 FP16: 24,294,400	116,800	379,600	7300	94.9	379.6	48.5/97 (2:1 sparse	97/194 (2:1 sparse	10240 (GPU) + 6124 (shared)			320	560			No		FP32: 12147.2 FP16: 24294.4	DirectX raytracing, FidelityFX Super Resolution - FSR, FSR 2, FSR 3, DirectML, 8K HDR support, variable refresh rate, 120 Hz support[694]
Oberon (PlayStation 5)	November 12, 2020			probably 10,600	2304:144:64:36	~2233 (Boost)	FP32: ~10,289,664 (Boost) FP16: 20,579,328 (Boost)	142,912 (Boost)	321,552 (Boost)	6400 (Boost)	-	-	-	-	16384 (shared)			256	448		No	4.6	Vulkan 1.3	FP32: 10289.6 (Boost) FP16: 20579.2 (Boost)	8K HDR support, 120 Hz support, FidelityFX Super Resolution (FSR), raytracing
Aerith (Steam Deck)	February 2022			probably ~2,400	512:32:16:8	~1000/~1600 (Boost)	FP32: ~1.024.000/ ~1,638,400 (Boost) FP16: ~2,048,000/ ~3,276,800 (Boost)	16,000/ 25,600 (Boost)	32,000/ 51,200 (Boost)	644/ 1020 (Boost)	8/ 12.8 (Boost)	36/ 51.2 (Boost)	-	-	16384 (shared)	2750 (5500 effective)	LPDDR5	128	88		No	4.6	Vulkan 1.3	FP32: 1024/ 1638.4 (Boost) FP16: 2048/ 3276.8 (Boost)	raytracing, FidelityFX Super Resolution (FSR), 8k resolution at 60 Hz or 4k resolution at 120 Hz (dock mode)
Radeon 740M - Phoenix (ROG Ally)	2023	RDNA 3	TSMC 4 nm	~25,000	256:16:8:4	2500 (Boost)	FP32: 2,560,000 (Boost) (dual-issue shader ALUs - Resulting in half of this value.)5 FP16: 5,120,000 (Boost) (dual-issue shader ALUs - Resulting in half of this value.)5	20,000 (Boost)	40,000 (Boost)	~750	~10 (Boost)	~40 (Boost)	-	-	16384 (shared)	3200 (6400 effective)			102.4		12U	4.6	Vulkan 1.3	FP32: 2560 (Boost) (dual-issue shader ALUs)5 FP16: 5120 (Boost) (dual-issue shader ALUs)5	raytracing, FidelityFX Super Resolution (FSR 1/2/3) DirectML
Radeon 780M - Phoenix (ROG Ally Extreme)					768:48:32:12	2700 (Boost)	FP32: 8,294,000 (Boost) (dual-issue shader ALU - Resulting in half of this value.s)5 FP16: 16,590,000 (Boost) (dual-issue shader ALUs - Resulting in half of this value.)5	86,400 (Boost)	129,600 (Boost)	~2300	~30 (Boost)	~120 (Boost)	-	-										FP32: 8294 (Boost) (dual-issue shader ALUs)5 FP16: 16590 (Boost) (dual-issue shader ALUs)5
Viola (PlayStation 5 Pro)	November 7, 2024	RDNA 3		~21000	3840:240:64:60	2170 (Boost)	FP32: 33,331,200 (Boost) (dual-issue shader ALUs - Resulting in half of this value.)5 FP16: 66,662,400 (Boost) (dual-issue shader ALUs - Resulting in half of this value.)5	138,880 (Boost)	520,800 (Boost)	-	-	-	150/300 (2:1 sparse (Boost)	-	16384 (shared) 2048	2250 (18000 effective)	GDDR6 DDR5	256	576		No	4.6	Vulkan 1.3	FP32: 16665.6 (Boost) FP16: 33331.2 (Boost)	8K HDR support, 120 Hz support, FidelityFX Super Resolution (FSR), raytracing, PlayStation Spectral Super Resolution (PSSR)
Code Name (Console Model)	Launch	GPU Code Name and/or Architecture	Fab (nm)	Transistors (million)	Core config1,2,3	Core clock (MHz)	Million Operations/s	Million Pixels/a	MTexels/s	MTri/s	GRays/s (triangles)	GRays/s (voxels or boxes)	TOPS (INT8)	TOPS (INT4)	Size (MiB)	Clock (MHz)	RAM type	Bus width (bit)	Bandwidth (GB/s)	Bus interface	Direct3D	OpenGL	Other	Processing power (GFLOPS)	Architecture features
							Fillrate				Ray-tracing Performance		ML Performance		Memory						API compliance (version)

¹ Pixel shaders : Vertex shaders : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units
³ Unified shaders : Texture mapping units : Render output units : RT Cores
⁴ The Latte looks similar to the RV730 used in the Radeon HD4650/4670.^[695]
5 In most cases, especially in games, half of this data can be considered.^[696]

See also

• List of Nvidia graphics processing units
• List of Intel graphics processing units
• List of AMD processors with 3D graphics
• Apple M1
• Video Coding Engine, AMD's equivalent SIP core till 2017
• Video Core Next, AMD's video core which combines the functionality of Video Coding Engine and Unified Video Decoder