M1 8GB vs M2 Ultra 192GB
For running local LLMs · 2 reports across 2 models
Tokens per second by model
| Model | M1 8GB | M2 Ultra 192GB |
|---|---|---|
| DeepSeek V3 | — | 28.0n=1 |
| Gemma 4up to 31B | 17.5n=1 | — |
For running local LLMs · 2 reports across 2 models
| Model | M1 8GB | M2 Ultra 192GB |
|---|---|---|
| DeepSeek V3 | — | 28.0n=1 |
| Gemma 4up to 31B | 17.5n=1 | — |