M2 Ultra 64GB vs RX 7600 8GB
For running local LLMs · 1 report across 1 model
Tokens per second by model
| Model | M2 Ultra 64GB | RX 7600 8GB |
|---|---|---|
| Gemma 4up to 31B | 14.0n=1 | — |
For running local LLMs · 1 report across 1 model
| Model | M2 Ultra 64GB | RX 7600 8GB |
|---|---|---|
| Gemma 4up to 31B | 14.0n=1 | — |