Mid-size: 10 to 70 billion
The workhorse open models: Llama 2 13B, Qwen 32B, Gemma 27B and their kin. 103 models.
🇺🇸 United StatesNorth Mini Code
A 30B sparse mixture-of-experts model for code and terminal agent workCode · Conditional licence
🇺🇸 United StatesOrca 2
A small LLaMA-2-based model trained on synthetic data to reason.Small · Conditional licence · 2023
🇫🇷 FranceMistral Saba
A 24B regional language model for Arabic and South Asian languagesRegional · API only · 2025