Will this model run on your hardware?
Can I run Mistral: Mistral Small 4 locally?
- 119B parameters (9.5B active, MoE)
- context up to 1024K
- licence: apache-2.0
- Weights: mistralai/Mistral-Small-4-119B-2603 · GGUF: unsloth/Mistral-Small-4-119B-2603-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 126.5 GB |
| UD-Q6_K | 99.4 GB |
| UD-Q5_K_M | 89.2 GB |
| UD-Q4_K_M | 73.8 GB |
| MXFP4 | 71.8 GB |
| UD-Q3_K_M | 54.4 GB |
Run it locally
ollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q4_K_M
llama serve -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q4_K_M
LM Studio: open unsloth/Mistral-Small-4-119B-2603-GGUF