← All free tools · 🧩 Open Source
LLaMA-Factory
✓ Verified against the official pageUnified fine-tuning for 100+ models: LoRA, SFT, DPO, web UI.
Free limit
Free limit
Open code: self-host free
Access type
Open source
Period
—
Watermark
Not verified
Commercial use
Yes
Credit card
Not verified
Sign-up
Not verified
API
Yes: Self-hosted OpenAI-style API via vLLM/SGLang worker: 'Deploy with OpenAI-style API and vLLM'; API docs link provided.
Resolution and duration limits
—
Regional restrictions
Not specified
Checked
Nov 22, 2026
LLaMA-Factory is an Apache-2.0 open-source project that can be used for free locally for model fine-tuning and inference; no usage limits are stated in the text. Separate free external resources are mentioned: a Colab notebook with a free T4 GPU, PAI-DSW (free trial) and AMD GPU Cloud (free credits).
What the tool does
SFT, LoRA, DPO, web UI, export.
Official source
We provided a Colab notebook for fine-tuning the Llama-3 model on a free T4 GPU.
- github.com/hiyouga/LLaMA-Factory — Nov 22, 2026 (43888 симв.)
Free-tier change history
| Field | Before | After | Date |
|---|---|---|---|
| No changes recorded yet. | |||