Instinct MI300X 192GB vs RTX 4070
For running local LLMs · 2 reports across 1 model
Tokens per second by model
| Model | Instinct MI300X 192GB | RTX 4070 |
|---|---|---|
| Gemma 4up to 31B | — | 55.0n=2 |
For running local LLMs · 2 reports across 1 model
| Model | Instinct MI300X 192GB | RTX 4070 |
|---|---|---|
| Gemma 4up to 31B | — | 55.0n=2 |