Q_pi
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Max | Q_pi | 8bit | oMLX | 16.2 | 255.2 | – | – | 1024 | 2026-10-06 | community | – | source |
| M4 Max | Q_pi | 8bit | oMLX | 15.3 | 218.2 | – | – | 4096 | 2026-10-06 | community | – | source |