RDNA 4

RDNA 4 is a GPU microarchitecture designed by AMD, released with the Radeon RX 9000 series on February 28, 2025.^[1]

RDNA 4

Launched	February 28, 2025; 7 months ago (2025-02-28)
Designed by	AMD
Manufactured by	TSMC
Fabrication process	TSMC N4P
Product Series
Desktop	Radeon RX 9000 series
Specifications
Compute	Up to 97.3 TFLOPS (FP16) Up to 48.7 TFLOPS (FP32) Up to 0.76 TFLOPS (FP64)
Clock rate	1700 MHz to 2530 MHz
L0 cache	64 KB (per WGP)
L1 cache	128 KB (per array)
L2 cache	8 MB
L3 cache	64 MB
Memory support	GDDR6
Memory clock rate	up to 20 Gbps
PCIe support	PCIe 5.0
Supported Graphics APIs
Direct3D	Direct3D 12.0 Ultimate (feature level 12_2)
Shader Model	Shader Model 6.7
OpenGL	OpenGL 4.6
Vulkan	Vulkan 1.4
Supported Compute APIs
OpenCL	OpenCL 2.1
Media Engine
Encode codecs	H.264 H.265 AV1
Decode codecs	H.264 H.265 AV1
Color bit-depth	8-bit 10-bit 12-bit
Encoders supported	AMF VCE
Display outputs	DisplayPort 2.1 HDMI 2.1a USB-C
History
Predecessor	RDNA 3
Successor	UDNA
Support status
Supported

Navi 4x dies

			Navi 44	Navi 48
Launch			Jun 2025	Mar 2025
Codename
Compute units (Stream processors) [FP32 cores]			32 (2048) [4096]	64 (4096) [8192]
Process			TSMC N4P
Transistors			29.7 bn.	53.9 bn.
Transistor density			149.2 MTr/mm2	151.1 MTr/mm2
Die size			199 mm2	356.5 mm2
Products	Consumer	Desktop	RX 9060XT RX 9060	RX 9070 XT RX 9070 GRE RX 9070
		Mobile	—	—
	Workstation	Desktop	—	—
		Mobile	—	—

Products

Gaming

Desktop

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)[2]	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)[3][4]	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)[5]	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)[6]	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)[7]	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).