Qwen2.5-Coder-3B-Instruct
8 records across 3 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M3 Max | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 116.7 | 1458.0 | – | – | 1024 | 2026-10-11 | community | – | source |
| M3 Max | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 107.3 | 1338.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 60.3 | 2045.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M5 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 56.4 | 2066.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M2 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 15.8 | 212.2 | – | – | 1024 | 2026-10-15 | community | – | source |
| M2 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 15.3 | 129.7 | – | – | 1024 | 2026-10-15 | community | – | source |
| M2 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 13.6 | 83.6 | – | – | 4096 | 2026-10-15 | community | – | source |
| M2 | Qwen2.5-Coder-3B-Instruct | 4bit | oMLX | 13.5 | 81.7 | – | – | 4096 | 2026-10-15 | community | – | source |