QUADRO RTX 6000 vs RTX 5090
The cheapest QUADRO RTX 6000 ($0.13) costs 43% less per hour than the cheapest RTX 5090 ($0.22).
Per unit of performance, the RTX 5090 is 28% cheaper: $0.24 versus $0.33 per A100-equivalent hour.
The RTX 5090 has 32 GB of memory against 24 GB on the QUADRO RTX 6000.
| Measure | NVIDIA Quadro RTX 6000 24GB | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Lowest per GPU-hour | $0.13 | $0.22 |
| Median per GPU-hour | $0.31 | $0.87 |
| On-demand from | $0.13 | $0.34 |
| Spot from | $0.13 | $0.25 |
| Reserved from | $0.81 | $0.22 |
| Lowest per A100-equivalent hour | $0.33 | $0.24 |
| Live offers | 21 | 405 |
| Providers | 15 | 84 |
| Memory | 24 GB GDDR6 | 32 GB GDDR7 |
| Memory bandwidth | 672 GB/s | 1,792 GB/s |
| FP16 / BF16 | 130.5 TFLOPS | 209.5 TFLOPS |
| FP8 | — | 419 TFLOPS |
| Performance vs A100 80GB | 0.38× | 0.92× |
| Architecture | Turing | Blackwell |
| Power | 295 W | 575 W |