AMD Radeon AI PRO R9700 vs NVIDIA A800 40GB Full Specs

Summary

4,096 Shaders 2.92GHz	6,912 Shaders 1.41GHz
32GB GDDR6640GB/s	40GB HBM2e1.55TB/s
Peak·FP32·FP16 47.84 TFLOPS	Peak·FP32·FP16 19.49 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 300W	TDP 250W
Power Connectors 1x 12-Pin -	Power Connectors - 1x 8-Pin EPS

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 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Radeon AI PRO R97001.53 POPSINT4 Tensor Sparse

x1

A800 40GB2.5 POPSINT4 Tensor Sparse

x1.63

Show Top Score

Theoretical Performance

Clock Speed2920MHz UC·Base·Boost·OC	Clock Speed1410MHz UC·Base·Boost·OC
Peak OPS 1.53 POPSINT4 Tensor Sparse	Peak OPS 2.5 POPSINT4 Tensor Sparse
Tensor FP8-16 191.4 TFLOPS FP8-16 Tensor Sparse 382.7 TFLOPS Tensor FP8-32 191.4 TFLOPS FP8-32 Tensor Sparse 382.7 TFLOPS	-
Tensor FP16-16 95.68 TFLOPS FP16-16 Tensor Sparse 191.4 TFLOPS Tensor FP16-32 95.68 TFLOPS FP16-32 Tensor Sparse 191.4 TFLOPS	Tensor FP16-16 311.9 TFLOPS FP16-16 Tensor Sparse 623.7 TFLOPS Tensor FP16-32 311.9 TFLOPS FP16-32 Tensor Sparse 623.7 TFLOPS
BF16 95.68 TFLOPS Tensor BF16 95.68 TFLOPS BF16 Tensor Sparse 191.4 TFLOPS	BF16 38.98 TFLOPS Tensor BF16 311.9 TFLOPS BF16 Tensor Sparse 623.7 TFLOPS
Tensor TF32 -	Tensor TF32 155.9 TFLOPS
FP32 47.84 TFLOPS	FP32 19.49 TFLOPS
FP64 1.5 TFLOPS Tensor FP64 -	FP64 9.75 TFLOPS Tensor FP64 19.49 TFLOPS
Tensor INT4 765.5 TOPS	Tensor INT4 1.25 POPS
Tensor INT8 382.7 TOPS	Tensor INT8 623.7 TOPS
Pixel Rate 373.8 GPixel/s	Pixel Rate 225.6 GPixel/s
Texture Rate 747.5 GTexel/s	Texture Rate 609.1 GTexel/s

Core Config

Shaders 4,096 Shaders	Shaders 6,912 Shaders
TMUs 256 TMUs	TMUs 432 TMUs
ROPs 128 ROPs	ROPs 160 ROPs
Tensor Cores 128 T-Cores	Tensor Cores 432 T-Cores
RT Cores 64 RT-Cores	RT Cores -
CUs 64 CUs	SMs 108 SMs

Clocks

Base Clock 2.4GHz	Base Clock 765MHz
Boost Clock 2.92GHz	Boost Clock 1.41GHz

Cache

L2 Cache 8.2MB shared	L2 Cache 41MB shared
L3 Cache 64MB shared	L3 Cache -
L3 Bandwidth 2.25TB/s	L3 Bandwidth -

Memory

32GB GDDR6	40GB HBM2e
Memory Bus 256-bit	Memory Bus 5120-bit
Memory Speed 20GT/s	Memory Speed 2.4GT/s
Memory Bandwidth 640GB/s	Memory Bandwidth 1.55TB/s
ECC No	ECC No

Power & Thermals

TDP 300W

TDP 250W

Video Output

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

Ports

3x DisplayPort 2.1	-
1x HDMI 2.1	-

Encoder

Encoder Model VCN 4.0

-

Decoder

Decoder Model VCN 4.0

Decoder Model 5x NVDEC 4

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2-Slots	PCIe 2-Slots
Height 111 mm (4.37") Width 241 mm (9.49") Depth 40 mm (1.57")	Height 111 mm (4.37") Width 267 mm (10.51") Depth 40 mm (1.57")
Cooling Blower 1x Fan	Cooling Passive -
Power Connectors 1x 12-Pin	Power Connectors 1x 8-Pin EPS

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 4	Architecture Ampere
Family Radeon AI PRO	Family Server
Branding	Branding
Codename -	Codename NV170
Chip Variant Navi 48 XL	Chip Variant -
Market Segment Workstation	Market Segment Server
Release Date May 20, 2025	Release Date Jun 28, 2021

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N4P	Fabrication Node 7N
Die Size 357mm²	Die Size 826mm²
Transistor Count 53.9 Billion	Transistor Count 54.2 Billion
Transistor Density 151.2 MTr/mm²	Transistor Density 65.62 MTr/mm²

Images

No images available

No images available

Competitors

AMDRadeon AI PRO R9700 vs GPU NVIDIARTX PRO 4500 Blackwell AMDRadeon AI PRO R9700 vs GPU AMDRadeon RX 9070 XT AMDRadeon AI PRO R9700 vs GPU NVIDIARTX 5000 Ada Show 12 more

NVIDIAA800 40GB vs GPU AMDInstinct MI300P NVIDIAA800 40GB vs GPU NVIDIARTX PRO 4500 Blackwell NVIDIAA800 40GB vs GPU NVIDIARTX PRO 5000 Blackwell Show 12 more