unsloth

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

⭐ 71,965 stars on GitHub · 🍴 6,486 forks · 📜 License: apache-2.0 · 💻 Language: Python

What is unsloth?

Running and fine-tuning local AI models usually requires a fragile web of Python scripts, CUDA dependencies, and fragmented CLI tools. Now there is a unified desktop application that packages inference, RAG, and hardware-accelerated training

Topics: the project is tagged with popular topics:

🏷️ agent
🏷️ ai
🏷️ chatgpt
🏷️ deepseek
🏷️ fine-tuning
🏷️ gemma
🏷️ image-generation
🏷️ llama
🏷️ llm
🏷️ llms

📸 Screenshots

unsloth desktop

![unsloth](https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png)

Quick install

See the README for detailed install instructions. Most projects support Docker — if the repo has a Dockerfile, use:

git clone https://github.com/unslothai/unsloth.git
cd unsloth
docker build -t unsloth .
docker run -d -p 8080:8080 unsloth

Minimum system requirements

Component	Recommended
RAM	4096 MB
CPU	2 vCPU
Disk	50 GB SSD
OS	Ubuntu 22.04 LTS / Debian 12
Docker	24.0+

⚡ Deploy fast on VSIS

Use the VSIS VPS Standard 4GB RAM / 2 vCPU / 50GB SSD (~150k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running unsloth smoothly.

🎯 Benefits:

One-command docker compose up -d deploy in 2 minutes
Dedicated IPv4, root access, unmetered domestic bandwidth
Daily snapshot backup
Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources

🔗 GitHub: unslothai/unsloth
🌐 Homepage: https://unsloth.ai/docs
📚 Official docs: see README in the repo
💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 15/08/2026. Star/fork counts may have changed — see live numbers via the GitHub link.