RTX 5000 ADA 32GB vs RTX 5090
The cheapest RTX 5090 ($0.22) costs 48% less per hour than the cheapest RTX 5000 ADA 32GB ($0.42).
Per unit of performance, the RTX 5090 is 62% cheaper: $0.24 versus $0.63 per A100-equivalent hour.
| Measure | NVIDIA RTX 5000 Ada Generation 32GB | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Lowest per GPU-hour | $0.42 | $0.22 |
| Median per GPU-hour | $0.84 | $0.87 |
| On-demand from | $0.42 | $0.34 |
| Spot from | — | $0.25 |
| Reserved from | $0.56 | $0.22 |
| Lowest per A100-equivalent hour | $0.63 | $0.24 |
| Live offers | 18 | 405 |
| Providers | 10 | 84 |
| Memory | 32 GB GDDR6 | 32 GB GDDR7 |
| Memory bandwidth | 576 GB/s | 1,792 GB/s |
| FP16 / BF16 | 261.1 TFLOPS | 209.5 TFLOPS |
| FP8 | 522.2 TFLOPS | 419 TFLOPS |
| Performance vs A100 80GB | 0.67× | 0.92× |
| Architecture | Ada Lovelace | Blackwell |
| Power | 250 W | 575 W |