M3 Max 48GB vs RX 7800 XT 16GB
For running local LLMs · 1 report across 1 model
Tokens per second by model
| Model | M3 Max 48GB | RX 7800 XT 16GB |
|---|---|---|
| Gemma 4up to 31B | 18.0n=1 | — |
For running local LLMs · 1 report across 1 model
| Model | M3 Max 48GB | RX 7800 XT 16GB |
|---|---|---|
| Gemma 4up to 31B | 18.0n=1 | — |