Mistral Medium 3.5 (128B, Q4)
Mistral AI's frontier dense 128B model with configurable reasoning (instant or chain-of-thought via reasoning_effort). Native function-calling, 256K context. Workstation-tier on-device — needs ~80GB of usable memory for Q4_K_M; an MLX 4-bit build is available for Apple Silicon Mac Studio-class hardware. License is a Modified MIT with a revenue carve-out — free for commercial and non-commercial use unless the licensee company exceeds Mistral's revenue threshold.
| At a glance | |
|---|---|
| Made by | Mistral AI |
| Download size | 74.9 GB |
| Parameters | 128B |
| Quantization | Q4_K_M |
| Context window | 262K tokens |
| Uses tools | Yes |
| Best for | Reasoning |
| Runs on | llama.cpp, MLX |
| License | MIT-Modified |
| Added to the catalog | 2026-08-15 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.