Mid-size: 10 to 70 billion
The workhorse open models: Llama 2 13B, Qwen 32B, Gemma 27B and their kin. 103 models.
🇺🇸 United StatesPhi
Microsoft's small open-weights language models that run on a single deviceSmall · Open weights · 2023
🇺🇸 United StatesTalkie
A 13B small language model trained only on pre-1931 public domain English textSmall · Open weights · 2026
🇺🇸 United StatesOrca 2
A small LLaMA-2-based model trained on synthetic data to reason.Small · Conditional licence · 2023
🇺🇸 United StatesPhi-3
Small Microsoft language models built to run well on phones and laptops.Small · Open weights · 2024
🇰🇷 South KoreaSOLAR 10.7B
An 11-billion parameter language model using depth up-scaling.General · Open weights · 2023
🇫🇷 FranceMistral Saba
A 24B regional language model for Arabic and South Asian languagesRegional · API only · 2025
🇫🇷 FranceDevstral
A 24B agentic coding model built by Mistral AI and All Hands AICode · Open weights · 2025
🇨🇳 ChinaKimi Linear
Hybrid linear attention model with 48 billion parametersGeneral · Open weights · 2025
WorldFathom-R1-14B
Low-cost open reasoning model for mathematicsReasoning · Open weights
🇨🇳 ChinaERNIE-4.5-21B-A3B-Thinking
Lightweight reasoning model with 21 billion parametersReasoning · Open weights · 2025
WorldJamba2 Mini
A small open-weights SSM-Transformer model for enterprise workSmall · Open weights
🇰🇷 South KoreaMi:dm 2.0
Korea-centric language model by KTGeneral · Open weights · 2025
🇺🇸 United StatesNorth Mini Code
A 30B sparse mixture-of-experts model for code and terminal agent workCode · Conditional licence
WorldRWKV-4
A dense recurrent model with transformer-level performanceGeneral · Open weights · 2023
🇺🇸 United StatesGranite 4.0
IBM's hybrid Mamba/transformer language models for enterprise workGeneral · Open weights · 2025