GPU Wiki
Compare NVIDIA GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | H100 CNX |
|---|---|
| Overview | |
| Product name | NVIDIA H100 CNX |
| Architecture | Hopper |
| Generation / family | NVIDIA H-Series |
| GPU codename | GH100 |
| Launch date | 2023-03-21 |
| Market segment | Data Center in NVIDIA H-Series |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | TSMC 5 nm |
| Die size | 814 mm² |
| Transistor count | 80 billion |
| GPU chip | GH100 |
| SM / multiprocessor count | 114 |
| CUDA Cores | 14592 |
| Tensor Cores | 456 |
| ROPs | 24 |
| TMUs | 456 |
| Clocks | |
| Base / Core clock | 690 MHz |
| Boost clock | 1,845 MHz |
| Memory clock | 1,593 MHz |
| Memory | |
| Memory size | 80 GB |
| Memory type | HBM2e |
| Memory bus width | 5,120-bit |
| Memory bandwidth | 2,040 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 5.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 350 W |
| Recommended PSU | 750 W |
| Power connectors | 8-pin EPS |
| Slot width | Dual-slot, 267 mm length |
| Features | |
| CUDA support | 9.0 |
| Performance / Benchmarks | |
| FP32 throughput | 53.84 TFLOPS |
| FP16 throughput | 215.4 TFLOPS |
Overview
Product name
H100 CNX
NVIDIA H100 CNX
Architecture
H100 CNX
Hopper
Generation / family
H100 CNX
NVIDIA H-Series
GPU codename
H100 CNX
GH100
Launch date
H100 CNX
2023-03-21
Market segment
H100 CNX
Data Center in NVIDIA H-Series
Board type / entry type
H100 CNX
Data Center GPU
GPU
Process node
H100 CNX
TSMC 5 nm
Die size
H100 CNX
814 mm²
Transistor count
H100 CNX
80 billion
GPU chip
H100 CNX
GH100
SM / multiprocessor count
H100 CNX
114
CUDA Cores
H100 CNX
14592
Tensor Cores
H100 CNX
456
ROPs
H100 CNX
24
TMUs
H100 CNX
456
Clocks
Base / Core clock
H100 CNX
690 MHz
Boost clock
H100 CNX
1,845 MHz
Memory clock
H100 CNX
1,593 MHz
Memory
Memory size
H100 CNX
80 GB
Memory type
H100 CNX
HBM2e
Memory bus width
H100 CNX
5,120-bit
Memory bandwidth
H100 CNX
2,040 GB/s
Bus / Interface
Bus interface
H100 CNX
PCIe 5.0 x16
AGP / PCI / PCIe distinction
H100 CNX
PCIe
Power
TDP / TBP / board power
H100 CNX
350 W
Recommended PSU
H100 CNX
750 W
Power connectors
H100 CNX
8-pin EPS
Slot width
H100 CNX
Dual-slot, 267 mm length
Display / Media
Features
CUDA support
H100 CNX
9.0
Performance / Benchmarks
FP32 throughput
H100 CNX
53.84 TFLOPS
FP16 throughput
H100 CNX
215.4 TFLOPS