M2 Ultra 192GB vs RTX 5090
For running local LLMs · 13 reports across 5 models
Tokens per second by model
| Model | M2 Ultra 192GB | RTX 5090 |
|---|---|---|
| Qwen3.6up to 35B | — | 3238.0n=7 |
| Gemma 4up to 31B | — | 578.0n=3 |
| DeepSeek V3 | 28.0n=1 | — |
| Kimi K2.6 | — | —n=1 |
| Qwen2.5 | — | —n=1 |
For running local LLMs · 13 reports across 5 models
| Model | M2 Ultra 192GB | RTX 5090 |
|---|---|---|
| Qwen3.6up to 35B | — | 3238.0n=7 |
| Gemma 4up to 31B | — | 578.0n=3 |
| DeepSeek V3 | 28.0n=1 | — |
| Kimi K2.6 | — | —n=1 |
| Qwen2.5 | — | —n=1 |