self-hosted/ai
§01·model · /models

Qwen3-4B

llmactiveApache-2.0

4B LLM by Alibaba (Qwen3) with hybrid thinking modes - strong small-model reasoning. Apache-2.0.

Download· 4 variants
§02·GPUs that run this model
4 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarksRecipe
RTX 3060 Ti8GB30~0recipecheck ↗
RTX 40608GB40~0recipecheck ↗
RTX 4060 Ti 8GB8GB40~0recipecheck ↗
RTX 50608GB50~0recipecheck ↗

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