LLaMA-Factory
A fine-tuning toolkit known for broad model support and an approachable web UI, which makes it one of the friendliest ways to start fine-tuning. It covers LoRA, QLoRA, full fine-tunes, and preference optimisation across many model families.
Strengths
- A web UI that lowers the barrier to a first fine-tune
- Very broad support across model families
- Apache 2.0, and covers the common tuning techniques
Weaknesses
- The GUI hides details you will eventually need to understand
- Serious runs still require capable GPU hardware
- Less scriptable for production than a config-first tool like Axolotl
At a glance
- Licence
- Apache 2.0
- Pricing
- Free
- Platforms
- Linux, Windows
- GPU required
- Yes
Links
Works with
Entry last verified 30 July 2026.