Devstral-Small-2-24B-Instruct-2512
20 records across 7 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 36.2 | 1094.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M5 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 35.2 | 1065.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M5 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 28.5 | 821.9 | – | – | 32768 | 2026-10-16 | community | – | source |
| M5 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 28.1 | 831.7 | – | – | 32768 | 2026-10-16 | community | – | source |
| M1 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 21.1 | 124.2 | – | – | 4096 | 2026-10-09 | community | – | source |
| M4 Max | Devstral-Small-2-24B-Instruct-2512 | 6bit | oMLX | 19.9 | 242.3 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Pro | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 19.9 | 457.8 | – | – | 1024 | 2026-10-11 | community | – | source |
| M5 Pro | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 19.9 | 457.8 | – | – | 1024 | 2026-10-11 | community | – | source |
| M2 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 19.6 | 148.7 | – | – | 16384 | 2026-10-16 | community | – | source |
| M5 Pro | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 19.1 | 478.4 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 Pro | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 19.1 | 478.4 | – | – | 4096 | 2026-10-11 | community | – | source |
| M2 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 18.6 | 147.1 | – | – | 16384 | 2026-10-16 | community | – | source |
| M4 Pro | Devstral-Small-2-24B-Instruct-2512 | mxfp4 | oMLX | 18.1 | 120.4 | – | – | 1024 | 2026-10-09 | community | – | source |
| M1 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 18.0 | 114.5 | – | – | 16384 | 2026-10-09 | community | – | source |
| M2 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 14.1 | 131.5 | – | – | 32768 | 2026-10-16 | community | – | source |
| M5 Max | Devstral-Small-2-24B-Instruct-2512 | 4bit | oMLX | 13.5 | 440.6 | – | – | 131072 | 2026-10-16 | community | – | source |
| M1 Max | Devstral-Small-2-24B-Instruct-2512 | 8bit | oMLX | 13.2 | 113.1 | – | – | 1024 | 2026-10-12 | community | – | source |
| M1 Max | Devstral-Small-2-24B-Instruct-2512 | 8bit | oMLX | 12.9 | 112.7 | – | – | 4096 | 2026-10-12 | community | – | source |
| M3 Pro | Devstral-Small-2-24B-Instruct-2512 | 6bit | oMLX | 6.4 | 111.4 | – | – | 4096 | 2026-10-09 | community | – | source |
| M3 Pro | Devstral-Small-2-24B-Instruct-2512 | 6bit | oMLX | 5.7 | 103.2 | – | – | 16384 | 2026-10-09 | community | – | source |