RDNA 4

RDNA 4
Launched	February 28, 2025; 3 months ago
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	2070 MHz to 2400 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
OpenCL	OpenCL 2.1
OpenGL	OpenGL 4.6
Vulkan	Vulkan 1.4
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;
Encoder(s) supported	AMF; VCE;
Display outputs	DisplayPort 2.1; HDMI 2.1a; USB-C;
History
Predecessor	RDNA 3
Successor	UDNA
Support status
	Supported

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

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	9060 XT	RX 9070 XT RX 9070 GRE RX 9070
	Consumer	Mobile	—	—
	Workstation	Desktop	—	—
	Workstation	Mobile	—	—

Model (Code name)	Release Date & Price	Architecture & fab	Transistors & die size	Core		Fillrate^[i]^[ii]^[iii]		Processing power					Infinity Cache		Memory				TBP	Bus interface
				Core		Fillrate^[i]^[ii]^[iii]		TFLOPS^[i]^[iv]			AI TOPS^[v]		Infinity Cache		Memory
				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 XT (Navi 44)^[2]^[3]	Jun 5, 2025 $299 USD $349 USD	RDNA 4 TSMC N4P	29.7 billion 199 mm²	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	GDDR6 128-bit	20000	150 W 160 W	PCIe 5.0 ×16
Radeon RX 9070 GRE (Navi 48)^[4]	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)^[5]	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	220 W
Radeon RX 9070 XT (Navi 48)^[6]	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	64 MB		16 GB	640	GDDR6 256-bit	20000	304 W

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