NVIDIA RTX 6000 Ada vs AMD Radeon PRO W7900 Full Specs

Summary

18,176 Shaders 2.5GHz	6,144 Shaders 2.5GHz
48GB GDDR6960GB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 91.06 TFLOPS	Peak·FP32·FP16 61.32 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 300W	TDP 295W
Power Connectors 1x 16-Pin 12VHPWR -	Power Connectors - 2x 8-Pin

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

RTX 6000 Ada2.91 POPSINT4 Tensor Sparse

x11.88

Radeon PRO W7900245.3 TOPSINT4 Tensor

x1

Show Top Score

Theoretical Performance

Clock Speed2505MHz UC·Base·Boost·OC	Clock Speed2495MHz UC·Boost·OC
Peak OPS 2.91 POPSINT4 Tensor Sparse	Peak OPS 245.3 TOPSINT4 Tensor
Tensor FP8-16 728.5 TFLOPS FP8-16 Tensor Sparse 1.46 PFLOPS Tensor FP8-32 364.2 TFLOPS FP8-32 Tensor Sparse 728.5 TFLOPS	-
Tensor FP16-16 364.2 TFLOPS FP16-16 Tensor Sparse 728.5 TFLOPS Tensor FP16-32 182.1 TFLOPS FP16-32 Tensor Sparse 364.2 TFLOPS	Tensor FP16-16 61.32 TFLOPS FP16-16 Tensor Sparse - Tensor FP16-32 61.32 TFLOPS FP16-32 Tensor Sparse -
BF16 91.06 TFLOPS Tensor BF16 182.1 TFLOPS BF16 Tensor Sparse 364.2 TFLOPS	BF16 122.6 TFLOPS Tensor BF16 61.32 TFLOPS BF16 Tensor Sparse -
Tensor TF32 91.06 TFLOPS	Tensor TF32 -
FP32 91.06 TFLOPS	FP32 61.32 TFLOPS
FP64 1.42 TFLOPS	FP64 1.92 TFLOPS
Tensor INT4 1.46 POPS	Tensor INT4 245.3 TOPS
Tensor INT8 728.5 TOPS	Tensor INT8 61.32 TOPS
Ray 210.5 TOPS	Ray -
Pixel Rate 481 GPixel/s	Pixel Rate 479 GPixel/s
Texture Rate 1.42 TTexel/s	Texture Rate 958.1 GTexel/s

Core Config

Shaders 18,176 Shaders	Shaders 6,144 Shaders
TMUs 568 TMUs	TMUs 384 TMUs
ROPs 192 ROPs	ROPs 192 ROPs
Tensor Cores 568 T-Cores	Tensor Cores 192 T-Cores
RT Cores 142 RT-Cores	RT Cores 96 RT-Cores
SMs 142 SMs	CUs 96 CUs

Clocks

Base Clock 915MHz	Base Clock -
Boost Clock 2.5GHz	Boost Clock 2.5GHz

Cache

L2 Cache 98.3MB shared	L2 Cache 6.1MB shared
L3 Cache -	L3 Cache 96MB shared
L3 Bandwidth -	L3 Bandwidth 3.5TB/s

Memory

48GB GDDR6	48GB GDDR6
Memory Bus 384-bit	Memory Bus 384-bit
Memory Speed 20GT/s	Memory Speed 18GT/s
Memory Bandwidth 960GB/s	Memory Bandwidth 864GB/s
ECC Yes	ECC -

Power & Thermals

TDP 300W

TDP 295W

Video Output

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

Ports

-	3x DisplayPort 2.1
4x DisplayPort 1.4	-
-	1x Mini DisplayPort 2.1

Encoder

Encoder Model 3x NVENC 8

Encoder Model VCN 4.0

Decoder

Decoder Model 3x NVDEC 5

Decoder Model VCN 4.0

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2-Slots	PCIe 3-Slots
Height 112 mm (4.41") Width 267 mm (10.51") Depth 40 mm (1.57")	Height 110 mm (4.33") Width 280 mm (11.02") Depth 51 mm (2.01")
Cooling Passive -	Cooling Blower 1x Fan
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 2x 8-Pin

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Ada Lovelace	Architecture RDNA 3
Family RTX Ada	Family Radeon PRO W
Branding	Branding
Codename NV182	Codename Plum Bonito
Chip Variant AD102-200-A1	Chip Variant Navi 31 XL
Market Segment Workstation	Market Segment Workstation
Release Date Dec 3, 2022	Release Date Apr 13, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries -	Other Foundries TSMCMCD
Fabrication Node 4N -	Fabrication Node N5 N6MCD
Die Size 608mm² -	Die Size 304mm² 225mm²MCD
Transistor Count 76.3 Billion -	Transistor Count 45.4 Billion 12.3 BillionMCD
Transistor Density 125.4 MTr/mm² -	Transistor Density 149.2 MTr/mm² 54.67 MTr/mm²MCD

Images

No images available

No images available

Competitors

NVIDIARTX 6000 Ada vs GPU NVIDIARTX 5880 Ada NVIDIARTX 6000 Ada vs GPU NVIDIARTX 5000 Ada NVIDIARTX 6000 Ada vs GPU NVIDIARTX PRO 5000 Blackwell Show 12 more

AMDRadeon PRO W7900 vs GPU NVIDIARTX 5000 Ada AMDRadeon PRO W7900 vs GPU NVIDIARTX 5880 Ada AMDRadeon PRO W7900 vs GPU NVIDIARTX PRO 5000 Blackwell Show 12 more