self-hosted/ai
§01·model · /models

Qwen3-4B

llmactiveApache-2.0

4B LLM by Alibaba with hybrid thinking modes and unusually strong reasoning for its size. Coverage here sits deliberately at the bottom of the range: all four cards with a recipe are 8 GB boards — the 3060 Ti, 4060, 4060 Ti 8GB and 5060 — which is exactly the point of a model this small. Apache-2.0.

Download· 4 variants
§02·same family
5 other models · by name

Other models grouped with Qwen3-4B. Sizes and modalities can differ, and nothing here says whether one fits your GPU — open a model for its own compatibility table.

§03·GPUs that run this model
4 total

benchmarked·~ runs via recipe (not benchmarked)· untested·doesn't fit