M1 Max 32GB vs M2 Max 32GB
For running local LLMs · 2 reports across 1 model
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 Max 32GB | M2 Max 32GB |
|---|---|---|
| Qwen3.8up to 2400B | 15.8n=2 | — |