M2 Max 96GB vs M3 Ultra 512GB
For running local LLMs · 11 reports across 5 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 | M2 Max 96GB | M3 Ultra 512GB |
|---|---|---|
| DeepSeek V4 Flashup to 285B | — | 20.0n=3 |
| Qwen3.6up to 35B | 28.0n=3 | — |
| DeepSeek V4.1 Flashup to 552B | — | 31.3n=2 |
| Qwen3.8up to 2400B | 22.0n=2 | — |
| Qwen3up to 235B | 43.0n=1 | — |