AMD Radeon PRO W7900 vs NVIDIA GeForce RTX 4090 Max-Q Full Specs

Summary

6,144 Shaders 2.5GHz	9,728 Shaders 1.46GHz
48GB GDDR6864GB/s	16GB GDDR6576GB/s
Peak·FP32·FP16 61.32 TFLOPS	Peak·FP32·FP16 28.31 TFLOPS
Form Factor PCIe Card	Form Factor Soldered
TDP 295W	TDP 80W
Power Connectors 2x 8-Pin	Power Connectors -

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Radeon PRO W7900245.3 TOPSINT4 Tensor

x1

GeForce RTX 4090 Max-Q905.9 TOPSINT4 Tensor Sparse

x3.69

Show Top Score

Theoretical Performance

Clock Speed2495MHz UC·Boost·OC	Clock Speed1455MHz UC·Base·Boost·OC
Peak OPS 245.3 TOPSINT4 Tensor	Peak OPS 905.9 TOPSINT4 Tensor Sparse
-	Tensor FP8-16 226.5 TFLOPS FP8-16 Tensor Sparse 452.9 TFLOPS Tensor FP8-32 113.2 TFLOPS FP8-32 Tensor Sparse 226.5 TFLOPS
Tensor FP16-16 61.32 TFLOPS FP16-16 Tensor Sparse - Tensor FP16-32 61.32 TFLOPS FP16-32 Tensor Sparse -	Tensor FP16-16 113.2 TFLOPS FP16-16 Tensor Sparse 226.5 TFLOPS Tensor FP16-32 56.62 TFLOPS FP16-32 Tensor Sparse 113.2 TFLOPS
BF16 122.6 TFLOPS Tensor BF16 61.32 TFLOPS BF16 Tensor Sparse -	BF16 28.31 TFLOPS Tensor BF16 56.62 TFLOPS BF16 Tensor Sparse 113.2 TFLOPS
Tensor TF32 -	Tensor TF32 28.31 TFLOPS
FP32 61.32 TFLOPS	FP32 28.31 TFLOPS
FP64 1.92 TFLOPS	FP64 442.3 GFLOPS
Tensor INT4 245.3 TOPS	Tensor INT4 452.9 TOPS
Tensor INT8 61.32 TOPS	Tensor INT8 226.5 TOPS
Ray -	Ray 65.43 TOPS
Pixel Rate 479 GPixel/s	Pixel Rate 163 GPixel/s
Texture Rate 958.1 GTexel/s	Texture Rate 442.3 GTexel/s

Core Config

Shaders 6,144 Shaders	Shaders 9,728 Shaders
TMUs 384 TMUs	TMUs 304 TMUs
ROPs 192 ROPs	ROPs 112 ROPs
Tensor Cores 192 T-Cores	Tensor Cores 304 T-Cores
RT Cores 96 RT-Cores	RT Cores 76 RT-Cores
CUs 96 CUs	SMs 76 SMs

Clocks

Base Clock -	Base Clock 930MHz
Boost Clock 2.5GHz	Boost Clock 1.46GHz

Cache

L2 Cache 6.1MB shared	L2 Cache 65.5MB shared
L3 Cache 96MB shared	L3 Cache -
L3 Bandwidth 3.5TB/s	L3 Bandwidth -

Memory

48GB GDDR6	16GB GDDR6
Memory Bus 384-bit	Memory Bus 256-bit
Memory Speed 18GT/s	Memory Speed 18GT/s
Memory Bandwidth 864GB/s	Memory Bandwidth 576GB/s

Power & Thermals

TDP 295W

TDP 80W

Video Output

Multi-Monitor 3	Multi-Monitor 4
HDCP HDCP 2.3	HDCP HDCP 2.3

Ports

3x DisplayPort 2.1	-
1x Mini DisplayPort 2.1	-

Encoder

Encoder Model VCN 4.0

Encoder Model 2x NVENC 8

Decoder

Decoder Model VCN 4.0

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor Soldered
PCIe 3-Slots	PCIe -
Height 110 mm (4.33") Width 280 mm (11.02") Depth 51 mm (2.01")	-
Cooling Blower 1x Fan	Cooling Open-Air -
Power Connectors 2x 8-Pin	Power Connectors -

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 3	Architecture Ada Lovelace
Family Radeon PRO W	Family GeForce 40
Branding	Branding
Codename Plum Bonito	Codename NV183
Chip Variant Navi 31 XL	Chip Variant AD103-275-A1
Market Segment Workstation	Market Segment Laptop
Release Date Apr 13, 2023	Release Date Feb 8, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCMCD	Other Foundries -
Fabrication Node N5 N6MCD	Fabrication Node 4N -
Die Size 304mm² 225mm²MCD	Die Size 379mm² -
Transistor Count 45.4 Billion 12.3 BillionMCD	Transistor Count 45.9 Billion -
Transistor Density 149.2 MTr/mm² 54.67 MTr/mm²MCD	Transistor Density 121.2 MTr/mm² -

Images

No images available

No images available

Competitors

AMDRadeon PRO W7900 vs GPU NVIDIARTX PRO 5000 Blackwell AMDRadeon PRO W7900 vs GPU NVIDIARTX PRO 4500 Blackwell AMDRadeon PRO W7900 vs GPU NVIDIARTX PRO 4000 Blackwell Show 12 more

NVIDIAGeForce RTX 4090 Max-Q vs GPU NVIDIAGeForce RTX 5080 Laptop 130W NVIDIAGeForce RTX 4090 Max-Q vs GPU NVIDIAGeForce RTX 5090 Laptop 95W NVIDIAGeForce RTX 4090 Max-Q vs GPU NVIDIAGeForce RTX 5080 Laptop 120W Show 12 more