M3 Max 128GB vs M5 Ultra 256GB
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 | M3 Max 128GB | M5 Ultra 256GB |
|---|---|---|
| Qwen3.6up to 35B | 5.5n=2 | — |