Qwen2.5-0.5B-Instruct
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Max | Qwen2.5-0.5B-Instruct | 4bit | oMLX | 201.1 | 3530.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| M1 Max | Qwen2.5-0.5B-Instruct | 4bit | oMLX | 198.3 | 3657.0 | – | – | 1024 | 2026-10-13 | community | – | source |