RTX 5090 vs RTX PRO 6000 Max-Q
For running local LLMs · 69 reports across 12 models
Highest reported generation speed by model family
These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →
| Model | RTX 5090 | RTX PRO 6000 Max-Q |
|---|---|---|
| Qwen3.8up to 2400B | 220.0n=34 | 240.0n=2 |
| DeepSeek V4 Flashup to 285B | 120.0n=10 | 44.0n=1 |
| Qwen3.6up to 35B | 215.1n=6 | — |
| Gemma 4up to 31B | 578.0n=4 | — |
| Museup to 30B | 253.0n=4 | — |
| DeepSeek V4 Pro | — | 7.1n=2 |
| GLM-5.2up to 744B | —n=1 | — |
| GLM-5.3 | 24.5n=1 | — |
| Kimi K2.5 | —n=1 | — |
| Qwen2.5up to 32B | —n=1 | — |
| Qwen3up to 235B | 159.0n=1 | — |
| Qwen3.5up to 122B | —n=1 | — |