Qwen2.5-32B-Instruct
6 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 28.1 | 734.9 | – | – | 1024 | 2026-10-13 | community | – | source |
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 28.1 | 734.9 | – | – | 1024 | 2026-10-13 | community | – | source |
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 28.0 | 787.3 | – | – | 1024 | 2026-10-13 | community | – | source |
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 26.9 | 794.1 | – | – | 4096 | 2026-10-13 | community | – | source |
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 26.9 | 794.1 | – | – | 4096 | 2026-10-13 | community | – | source |
| M5 Max | Qwen2.5-32B-Instruct | 4bit | oMLX | 26.7 | 807.3 | – | – | 4096 | 2026-10-13 | community | – | source |