granite-4.1-3b
4 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Max | granite-4.1-3b | mxfp4 | oMLX | 168.5 | 1973.0 | – | – | 1024 | 2026-10-14 | community | – | source |
| M5 | granite-4.1-3b | mxfp4 | oMLX | 62.8 | 1955.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M5 | granite-4.1-3b | mxfp4 | oMLX | 61.2 | 1958.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M5 | granite-4.1-3b | mxfp4 | oMLX | 60.9 | 1913.0 | – | – | 1024 | 2026-10-15 | community | – | source |