Mistral-Small-4-119B-2603
7 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | Mistral-Small-4-119B-2603 | 4bit | oMLX | 86.8 | 1507.0 | – | – | 1024 | 2026-10-07 | community | – | source |
| M5 Max | Mistral-Small-4-119B-2603 | 4bit | oMLX | 78.7 | 2556.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| Radeon 8060S | Mistral-Small-4-119B-2603 | UD-Q4_K_XL | llama.cpp | 41.2 | – | – | – | – | 2026-10-14 | sourced | – | source |
| Radeon 8060S | Mistral-Small-4-119B-2603 | UD-Q4_K_XL | llama.cpp | 39.5 | – | – | – | – | 2026-10-14 | sourced | – | source |
| Radeon 8060S | Mistral-Small-4-119B-2603 | UD-Q4_K_XL | llama.cpp | 3.4 | – | – | – | – | 2026-10-14 | sourced | – | source |
| Radeon 8060S | Mistral-Small-4-119B-2603 | UD-Q4_K_XL | llama.cpp | – | 334 | – | – | – | 2026-10-14 | sourced | – | source |
| Radeon 8060S | Mistral-Small-4-119B-2603 | UD-Q4_K_XL | llama.cpp | – | 319 | – | – | – | 2026-10-14 | sourced | – | source |