Mid-size: 10 to 70 billion
The workhorse open models: Llama 2 13B, Qwen 32B, Gemma 27B and their kin. 103 models.
馃嚭馃嚫 United StatesGranite 4.0
IBM's hybrid Mamba/transformer language models for enterprise workGeneral 路 Open weights 路 2025
馃嚭馃嚫 United StatesPhi-3
Small Microsoft language models built to run well on phones and laptops.Small 路 Open weights 路 2024
馃嚚馃嚦 ChinaKimi Linear
Hybrid linear attention model with 48 billion parametersGeneral 路 Open weights 路 2025
馃嚚馃嚦 ChinaERNIE-4.5-21B-A3B-Thinking
Lightweight reasoning model with 21 billion parametersReasoning 路 Open weights 路 2025