gemma-3-4b-it
4 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | gemma-3-4b-it | 4bit | oMLX | 92.2 | 4192.0 | – | – | 131072 | 2026-10-17 | community | – | source |
| M5 Max | gemma-3-4b-it | 4bit | oMLX | 92.2 | 4192.0 | – | – | 131072 | 2026-10-17 | community | – | source |
| M5 Max | gemma-3-4b-it | 4bit | oMLX | 73.3 | 3515.0 | – | – | 199680 | 2026-10-17 | community | – | source |
| M5 Max | gemma-3-4b-it | 4bit | oMLX | 73.3 | 3515.0 | – | – | 199680 | 2026-10-17 | community | – | source |