A100 SXM 80GB vs V100 32GB
The cheapest V100 32GB ($0.017) costs 97% less per hour than the cheapest A100 SXM 80GB ($0.61).
Per unit of performance, the V100 32GB is 93% cheaper: $0.04 versus $0.61 per A100-equivalent hour.
The A100 SXM 80GB has 80 GB of memory against 32 GB on the V100 32GB.
| Measure | NVIDIA A100 80GB SXM4 | NVIDIA Tesla V100 32GB |
|---|---|---|
| Lowest per GPU-hour | $0.61 | $0.017 |
| Median per GPU-hour | $1.71 | $2.32 |
| On-demand from | $0.68 | $0.017 |
| Spot from | $0.86 | $0.51 |
| Reserved from | $0.61 | $0.19 |
| Lowest per A100-equivalent hour | $0.61 | $0.04 |
| Live offers | 288 | 193 |
| Providers | 68 | 43 |
| Memory | 80 GB HBM2e | 32 GB HBM2 |
| Memory bandwidth | 2,039 GB/s | 900 GB/s |
| FP16 / BF16 | 312 TFLOPS | 125 TFLOPS |
| FP8 | — | — |
| Performance vs A100 80GB | 1× | 0.42× |
| Architecture | Ampere | Volta |
| Power | 400 W | 300 W |