Will this model run on your hardware?
Can I run Mistral: Ministral 3 8B 2512 locally?
- 8.9B parameters
- context up to 256K
- licence: apache-2.0
- Weights: mistralai/Ministral-3-8B-Instruct-2512 · GGUF: mistralai/Ministral-3-8B-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 | 9.0 GB |
| Q5_K_M | 6.1 GB |
| Q4_K_M | 5.2 GB |
Run it locally
ollama run hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
llama serve -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M