P100 16GB vs RTX 5090
The cheapest P100 16GB ($0.067) costs 69% less per hour than the cheapest RTX 5090 ($0.22).
Per unit of performance, the RTX 5090 is 53% cheaper: $0.24 versus $0.51 per A100-equivalent hour.
The RTX 5090 has 32 GB of memory against 16 GB on the P100 16GB.
| Measure | NVIDIA Tesla P100 16GB | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Lowest per GPU-hour | $0.067 | $0.22 |
| Median per GPU-hour | $1.18 | $0.87 |
| On-demand from | $0.067 | $0.34 |
| Spot from | — | $0.25 |
| Reserved from | $0.15 | $0.22 |
| Lowest per A100-equivalent hour | $0.51 | $0.24 |
| Live offers | 108 | 405 |
| Providers | 11 | 84 |
| Memory | 16 GB HBM2 | 32 GB GDDR7 |
| Memory bandwidth | 732 GB/s | 1,792 GB/s |
| FP16 / BF16 | 21.2 TFLOPS | 209.5 TFLOPS |
| FP8 | — | 419 TFLOPS |
| Performance vs A100 80GB | 0.13× | 0.92× |
| Architecture | Pascal | Blackwell |
| Power | 300 W | 575 W |