M3 Max 36GB vs RTX 4070
For running local LLMs · 3 reports across 1 model
Tokens per second by model
| Model | M3 Max 36GB | RTX 4070 |
|---|---|---|
| Gemma 4up to 31B | 16.0n=1 | 55.0n=2 |
For running local LLMs · 3 reports across 1 model
| Model | M3 Max 36GB | RTX 4070 |
|---|---|---|
| Gemma 4up to 31B | 16.0n=1 | 55.0n=2 |