gemma-4-31B-it-qat-q4_0-unquantized
6 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 24.1 | 237.8 | – | – | 4096 | 2026-10-10 | community | – | source |
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 24.1 | 237.8 | – | – | 4096 | 2026-10-10 | community | – | source |
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 24.1 | 236.3 | – | – | 4096 | 2026-10-10 | community | – | source |
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 21.7 | 237.9 | – | – | 1024 | 2026-10-10 | community | – | source |
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 21.7 | 237.9 | – | – | 1024 | 2026-10-10 | community | – | source |
| M1 Ultra | gemma-4-31B-it-qat-q4_0-unquantized | oQ4e | oMLX | 21.7 | 237.9 | – | – | 1024 | 2026-10-10 | community | – | source |