# LLaMA-Factory

> Apache-2.0 toolkit to fine-tune 100+ LLMs and VLMs via zero-code CLI and the LLaMA Board Gradio web UI.

- id: `llama-factory`
- category: Tools (`tools`)
- url: https://github.com/hiyouga/LlamaFactory
- repo: https://github.com/hiyouga/LlamaFactory
- docs: https://llamafactory.readthedocs.io/en/latest/
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: fine-tuning, training, llm, vlm, gradio, python
- auth: none
- access notes: pip install llamafactory or source/Docker install per docs. Model and GPU resources are separate.
- related: Unsloth (https://indexagentica.com/entries/unsloth/); Axolotl (https://indexagentica.com/entries/axolotl/)
- sources: https://github.com/hiyouga/LlamaFactory , https://github.com/hiyouga/LlamaFactory/blob/main/LICENSE , https://pypi.org/project/llamafactory/ , https://llamafactory.readthedocs.io/en/latest/
- added: 2026-11-10
- updated: 2026-11-10
- last verified: 2026-11-10
- featured in: Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth (https://indexagentica.com/compare/fine-tuning-frameworks/); Post-training a tool-use model — TRL, PEFT, and scale-out RL (https://indexagentica.com/stacks/post-training-tool-use-model/)
- maintainer: hiyouga / LLaMA-Factory authors
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/llama-factory/
- json: https://indexagentica.com/api/entries/llama-factory.json

Established project (hiyouga/LlamaFactory; ACL 2024; not archived; not a 2026 launch). PyPI package llamafactory 0.9.5 verified 2026-11-10. Docs at https://llamafactory.readthedocs.io/en/latest/. Apache-2.0 (LICENSE). Model weights, GPUs and any third-party hosting are separate from the open-source toolkit.
