Mistral (Ministral, Magistral, Devstral)
European open models. Ministral 3 14B for chat, Devstral for code.
FreeOpen sourceRuns on your PC
- Best for
- Chat in European languages
- On your PC
- Some setup
- Works on
- Windows, Mac, Linux
- License
- Apache-2.0
What’s good
- Fits a 12 GB card or 16 GB Mac
- Reads images, good in French, German, Spanish
- Devstral Small 2 (24B) is a solid local coder
Downsides
- Small models not updated since December 2025
- Behind Qwen3.8 and Gemma 4 on hard questions
- Magistral reasoning model is older (September 2025)
The details.
- Version
- Ministral 3 14BReleased 2025-12
- Open source
- Yes, Apache-2.0
- Made by
- Mistral AI
- Website
- mistral.ai
Should you use it?
It is #6 of 10. Good for chat in european languages; for most people, Qwen is the better start.
Can I run it myself?
Yes. Some setup: download a model inside an app.
Use LM Studio, Ollama, Jan, llama.cpp.
- You need
- 12 GB graphics card or Mac with 16 GB memory
- Setup
- Some setupDownload a model inside an app
- Laptop, 8 GBToo small
- PC, 16 GB+Too small
- Mac, 16 GBRuns
- Mac, 32 GBRuns
- Mac, 64 GB+Runs
- PC, 8 GB GPUToo small
- PC, 12 GB GPURuns
- PC, 16 GB GPURuns
- PC, 24 GB GPURuns
- WorkstationRuns