Instinct MI250X 128GB vs RTX 3060 12GB
For running local LLMs · 3 reports across 1 model
Tokens per second by model
| Model | Instinct MI250X 128GB | RTX 3060 12GB |
|---|---|---|
| Gemma 4up to 31B | — | 60.0n=3 |
For running local LLMs · 3 reports across 1 model
| Model | Instinct MI250X 128GB | RTX 3060 12GB |
|---|---|---|
| Gemma 4up to 31B | — | 60.0n=3 |