A16 vs RTX 5090
The cheapest A16 ($0.058) costs 74% less per hour than the cheapest RTX 5090 ($0.22).
Per unit of performance, the RTX 5090 is 56% cheaper: $0.24 versus $0.53 per A100-equivalent hour.
The RTX 5090 has 32 GB of memory against 16 GB on the A16.
| Measure | A16 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Lowest per GPU-hour | $0.058 | $0.22 |
| Median per GPU-hour | $0.53 | $0.87 |
| On-demand from | $0.082 | $0.34 |
| Spot from | — | $0.25 |
| Reserved from | $0.058 | $0.22 |
| Lowest per A100-equivalent hour | $0.53 | $0.24 |
| Live offers | 26 | 405 |
| Providers | 3 | 84 |
| Memory | 16 GB GDDR6 | 32 GB GDDR7 |
| Memory bandwidth | 200 GB/s | 1,792 GB/s |
| FP16 / BF16 | 35.9 TFLOPS | 209.5 TFLOPS |
| FP8 | — | 419 TFLOPS |
| Performance vs A100 80GB | 0.11× | 0.92× |
| Architecture | Ampere | Blackwell |
| Power | 62 W | 575 W |