Qwen2.5-14B
4 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4090D | Qwen2.5-14B 14B dense | FP8 | vLLM | 1131.19 | – | – | – | – | 2026-03 | community | – | source |
| 4090D | Qwen2.5-14B 14B dense | W4A16 | vLLM | 1079.15 | – | – | – | – | 2026-03 | community | – | source |
| M4 | Qwen2.5-14B | 4bit | oMLX | 12.2 | 123.0 | – | – | 1024 | 2026-10-09 | community | – | source |
| M4 | Qwen2.5-14B | 4bit | oMLX | 11.5 | 118.5 | – | – | 4096 | 2026-10-09 | community | – | source |