Will this model run on your hardware?
Can I run Mistral: Devstral 2 2512 locally?
- 125B parameters
- context up to 256K
- licence: other
- Weights: mistralai/Devstral-2-123B-Instruct-2512 · GGUF: unsloth/Devstral-2-123B-Instruct-2512-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 | 132.9 GB |
| Q6_K | 102.6 GB |
| Q5_K_M | 88.3 GB |
| Q4_K_M | 74.9 GB |
| Q3_K_M | 60.6 GB |
| Q2_K | 46.6 GB |
Run it locally
ollama run hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_K_M
llama serve -hf unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_K_M