M5 Max 128GB vs RTX Pro 6000 Blackwell
For running local LLMs · 45 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 | M5 Max 128GB | RTX Pro 6000 Blackwell |
|---|---|---|
| Qwen3.8up to 2400B | 55.0n=5 | 177.0n=16 |
| Qwen3.6up to 35B | 79.4n=3 | 600.0n=5 |
| DeepSeek V4 Flashup to 285B | —n=1 | 45.0n=4 |
| Museup to 30B | — | 57.0n=2 |
| Tencent-HY3up to 295B | 32.4n=1 | 57.4n=1 |
| GLM-5.3up to 321B | 24.0n=1 | — |
| Gemma 4up to 31B | 7.5n=1 | — |
| Llama 3.2up to 1B | — | —n=1 |
| Mimo 2.5 | — | —n=1 |
| Nex-N2.5-mini | 133.6n=1 | — |
| Qwen3.5up to 122B | —n=1 | — |
| StepFun 3.7 | 33.9n=1 | — |