AMD Radeon PRO W7700 vs NVIDIA H100 PCIe
GPU · Specs Compare
Graphics Card
Release Date
Nov 2023
Mar 2022
Generation
Radeon Pro Navi
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1900 MHz
1095 MHz
Boost Clock
2600 MHz
1755 MHz
Memory Clock
2250 MHz
1593 MHz
Memory
Memory Size
16GB
80GB
Memory Type
GDDR6
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
576.0GB/s
2039GB/s
Render Config
Compute Units
48
—
Shading Units
3072
14592
TMUs
192
456
ROPs
96
24
RT Cores
48
—
L1 Cache
128 KB per Array
256 KB (per SM)
L2 Cache
2 MB
50 MB
L3 Cache
64 MB
—
SM Count
—
114
Tensor Cores
—
456
Theoretical Performance
Pixel Rate
249.6 GPixel/s
42.12 GPixel/s
Texture Rate
499.2 GTexel/s
800.3 GTexel/s
FP16 (half)
63.90 TFLOPS
204.9 TFLOPS
FP32 (float)
31.95 TFLOPS
51.22 TFLOPS
FP64 (double)
998.4 GFLOPS
25.61 TFLOPS
Graphics Processor
GPU Name
Navi 32
GH100
GPU Variant
Navi 32
—
Architecture
RDNA 3.0
Hopper
Foundry
TSMC
TSMC
Process Size
5 nm
4 nm
Transistors
28.1 billion
80 billion
Die Size
346 mm²
814 mm²
Board Design
TDP
190W
350W
Suggested PSU
450 W
750 W
Outputs
4x DisplayPort 2.1
No outputs
Power Connectors
1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
2.2
3.0
Vulkan
1.3
N/A
Shader Model
6.7
N/A
CUDA
—
9.0
Benchmark
3DMark Time Spy
15,693
—
3DMark Speed Way
3,224
—
Blender
1,910
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.