NVIDIA H100 CNX vs NVIDIA H200 NVL
GPU · Specs Compare
Graphics Card
Release Date
Mar 2023
Nov 2024
Generation
Tesla Hopper
Server Hopper
Type
AI GPU
AI GPU
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
690 MHz
1365 MHz
Boost Clock
1845 MHz
1785 MHz
Memory Clock
1593 MHz
1593 MHz
Memory
Memory Size
80GB
141GB
Memory Type
HBM2e
HBM3e
Memory Bus
5120bit
6144bit
Bandwidth
2039GB/s
4.89TB/s
Render Config
SM Count
114
132
Shading Units
14592
16896
TMUs
456
528
ROPs
24
24
Tensor Cores
456
528
L1 Cache
256 KB (per SM)
256 KB (per SM)
L2 Cache
50 MB
50 MB
Theoretical Performance
Pixel Rate
44.28 GPixel/s
42.84 GPixel/s
Texture Rate
841.3 GTexel/s
942.5 GTexel/s
FP16 (half)
215.4 TFLOPS
241.3 TFLOPS
FP32 (float)
53.84 TFLOPS
60.32 TFLOPS
FP64 (double)
26.92 TFLOPS
30.16 TFLOPS
Graphics Processor
GPU Name
GH100
GH100
Architecture
Hopper
Hopper
Foundry
TSMC
TSMC
Process Size
4 nm
5 nm
Transistors
80 billion
80 billion
Die Size
814 mm²
814 mm²
Board Design
TDP
350W
600W
Suggested PSU
750 W
1000 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
8-pin EPS
Graphics Features
DirectX
N/A
N/A
OpenGL
N/A
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
9.0
9.0
Shader Model
N/A
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.