NVIDIA H100 PCIe 96 GB vs AMD Radeon Pro WX 4100
GPU · Specs Compare
Graphics Card
Release Date
Mar 2023
Nov 2016
Generation
Tesla Hopper
Radeon Pro
Type
AI GPU
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x8
Clock Speeds
Base Clock
1665 MHz
1125 MHz
Boost Clock
1837 MHz
1201 MHz
Memory Clock
1313 MHz
1500 MHz
Memory
Memory Size
96GB
4GB
Memory Type
HBM3
GDDR5
Memory Bus
5120bit
128bit
Bandwidth
1681GB/s
96.00GB/s
Render Config
SM Count
132
—
Shading Units
16896
1024
TMUs
528
64
ROPs
24
16
Tensor Cores
528
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
1024 KB
Compute Units
—
16
Theoretical Performance
Pixel Rate
44.09 GPixel/s
19.22 GPixel/s
Texture Rate
969.9 GTexel/s
76.86 GTexel/s
FP16 (half)
248.3 TFLOPS
2.460 TFLOPS
FP32 (float)
62.08 TFLOPS
2.460 TFLOPS
FP64 (double)
31.04 TFLOPS
153.7 GFLOPS
Graphics Processor
GPU Name
GH100
Baffin
Architecture
Hopper
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
4 nm
14 nm
Transistors
80 billion
3 billion
Die Size
814 mm²
123 mm²
GPU Variant
—
Baffin XT
Board Design
TDP
700W
50W
Suggested PSU
1100 W
250 W
Outputs
No outputs
4x mini-DisplayPort 1.4a
Power Connectors
8-pin EPS
None
Graphics Features
DirectX
N/A
12 (12_0)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
9.0
—
Shader Model
N/A
6.4
Benchmark
3DMark Time Spy
—
1,520
3DMark Time Spy Extreme
—
774
▲ Specs Compare
Data sourced from official specifications and benchmark tests.