M1 Ultra 128GB vs M2 Max 96GB
For running local LLMs · 8 reports across 4 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 | M1 Ultra 128GB | M2 Max 96GB |
|---|---|---|
| Qwen3.6up to 35B | — | 28.0n=3 |
| Qwen3.8up to 2400B | 31.2n=1 | 22.0n=2 |
| DeepSeek V4up to 284B | 16.0n=1 | — |
| Qwen3up to 235B | — | 43.0n=1 |