M2 Ultra 192GB vs RX 9070
For running local LLMs · 2 reports across 2 models
Tokens per second by model
| Model | M2 Ultra 192GB | RX 9070 |
|---|---|---|
| DeepSeek V3 | 28.0n=1 | — |
| Qwen3.6up to 35B | — | 46.9n=1 |
For running local LLMs · 2 reports across 2 models
| Model | M2 Ultra 192GB | RX 9070 |
|---|---|---|
| DeepSeek V3 | 28.0n=1 | — |
| Qwen3.6up to 35B | — | 46.9n=1 |