unslothai/unsloth

⭐ Features

Unsloth works on Windows, Linux, WSL and macOS. We support Multi GPU setups, NVIDIA, AMD, Intel GPUs, CPUs and the Vulkan backend.

Train & Deploy

• Fine-tuning: Train LLMs, diffusion, decision, TTS, and embedding models 2× faster with 70% less VRAM with no accuracy loss
• Complete support: Supports reinforcement learning, LoRA, QLoRA, full fine tuning, pretraining, RL, GRPO, DPO, and FP8.
• Export & Deploy: Export or Deploy models including GGUF, NVFP4, FP8 and more formats.
• Datasets: Build datasets from PDFs, CSVs, DOCX files, and more with Data Recipes.

📥 Install

Unsloth can be used in three ways: Unsloth Desktop, the desktop app; Unsloth Studio, the web UI; or Unsloth Core, the code based version.

📥 Advanced Installation

The below advanced instructions are for Unsloth Studio. For Unsloth Core advanced installation, view our docs.

Developer / Nightly / Experimental installs: macOS, Linux, WSL: The developer install builds from the main branch, which is the latest (nightly) source.

To install into an isolated location, set UNSLOTHSTUDIOHOME:

Developer / Nightly / Experimental installs: Windows PowerShell: The developer install builds from the main branch, which is the latest (nightly) source.

git clone https://github.com/unslothai/unsloth
cd unsloth
./install.sh --local
unsloth studio -p 8888

⚡ Get started

Download the native Unsloth Desktop app for your operating system: Platform Link Windows Download macOS Download Linux / Ubuntu (deb) Download Linux / Ubuntu (ARM64) (deb) Download Linux (AppImage) Download Windows (ARM64) Download

The Unsloth Docker image unsloth/unsloth is available on Docker. Read guide.

• 𝕏 (Twitter)

Run & Build with AI

• Run and train LLMs, MLX, GGUF, diffusion, decision, embedding, audio models: Qwen3.8, GLM-5.3-Flash, Kimi K3, Qwen-Image-2.1, MiniMax-H3, DeepSeek-V4, Gemma 4.
• Agents & Tools: Use local models with Claude Code, Codex, and MCP, including tool calling and code execution.
• Search & RAG: Use private and unlimited web search, deep research, auto-compaction (rolling context window) and RAG.
• Image and video: Run and train image and video diffusion or multimodal models
• Remote & LAN: Access your local models from any device on LAN or remotely through secure Cloudflare HTTPS.
• Connect: Serve models through an OpenAI compatible API. Also connect your ChatGPT/Codex subscription and cloud providers

🚀 Unsloth Start

Unsloth Start connects Claude Code, Codex and other agents to local models with one command.

• Claude Code — unsloth start claude
• OpenAI Codex — unsloth start codex
• Visual Studio Code — unsloth start vscode
• DeepSeek Harness — unsloth start dsh
• OpenCode — unsloth start opencode
• Hermes Agent — unsloth start hermes
• Pi — unsloth start pi
• OpenClaw — unsloth start openclaw
• Mistral Vibe — unsloth start vibe