Mellum2-12B-A2.5B-Thinking
10 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 128.5 | 1327.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 120.9 | 1218.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 116.0 | 1186.0 | – | – | 8192 | 2026-10-16 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 113.2 | 1155.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 108.2 | 1118.0 | – | – | 16384 | 2026-10-16 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 107.8 | 1113.0 | – | – | 16384 | 2026-10-16 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 100.3 | 1074.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 93.6 | 977.3 | – | – | 32768 | 2026-10-16 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 90.7 | 929.2 | – | – | 32768 | 2026-10-15 | community | – | source |
| M2 Max | Mellum2-12B-A2.5B-Thinking | 4bit | oMLX | 75.9 | 766.9 | – | – | 65536 | 2026-10-15 | community | – | source |