Mistral Small 3
Le modèle 24B de Mistral AI de janvier 2025 — Apache 2.0, compétitif avec Llama 3.3 70B, tient sur un seul GPU 24 Go.
Ressources D-Central : MMLU-Pro
Related products, repair, and setup paths
- self-hosted AI for Bitcoiners hub
- plebs guide to self-hosted AI
- install Ollama in 10 minutes
- LM Studio vs Ollama vs llama.cpp
- connect local AI to Home Assistant and Obsidian
- self-hosted AI troubleshooting
- repurpose mining hardware into an AI hashcenter
- local AI model leaderboards
Last reviewed 16 avril 2026.