Compare GPUs
| Spec | H100 | NVIDIA A100 80GB PCIe |
|---|---|---|
| Provider | AWS | RunPod |
| VRAM | 80 GB | 80 GB |
| Architecture | — | — |
| Compute cap. | — | — |
| Mem. bandwidth | — | — |
| GPUs / instance | 1 | 1 |
| vCPU | — | — |
| System RAM | — | — |
| Network | — | — |
| CUDA cores | — | 6,912 |
| Tensor cores | — | 432 |
| TDP | — | 400 W |
| Interconnect | — | PCIe |
| Per hour | $6.88/hr | $1.59/hr |
| Per month | — | $1160.70 |
| Available | Yes | Yes |
| Regions | — | — |
Observed · read from provider listings, not ranked