🦥Unsloth Docs

Unsloth is an open-source framework for running and training LLMs.

Unsloth lets you run and train AI models on your own local hardware via an open-source UI.

Our docs will guide you through running & training your own LLM locally.

Download Unsloth Features GitHub

Introducing Unsloth Desktop

The first desktop app to run and train LLMs and diffusion models.

Meta Muse Glimmer

Meta's new open Muse Glimmer 30B model.

DeepSeek-V4-Flash-0731

The new 284B model released on July 31.

Kimi K3

Run the strongest open model locally.

Unsloth Start

Connect to your agent to any local LLM.

⚡ Quickstart

Unsloth supports MacOS, Linux, Windows, NVIDIA, AMD, Intel and CPU setups. See: Unsloth Requirements. Download the native desktop app for your operating system:

Download Unsloth Desktop

Or, if you prefer manual installation:

MacOS, Linux, WSL:

curl -fsSL https://unsloth.ai/install.sh | sh

Windows PowerShell:

irm https://unsloth.ai/install.ps1 | iex

Complete LLM Directory 🧬Fine-tuning Guide

🔮Models Unsloth API

Then open http://127.0.0.1:8888 (or your specific URL) in your browser.

👾 Unsloth Start

Unsloth Start lets you connect Claude Code, Codex and other agents to local models via the unsloth start command.

Start Unsloth, load a model, open your project folder, and then run:

unsloth start claude

Replace claude with any agent below:

Agent

Command

Claude Code

unsloth start claude

OpenAI Codex

unsloth start codex

Hermes Agent

unsloth start hermes

OpenClaw

unsloth start openclaw

OpenCode

unsloth start opencode

🦥 Why Unsloth?

We directly collab with teams behind gpt-oss, Qwen3, Llama 4, Mistral, Gemma 1-3 and Phi-4, where we’ve fixed critical bugs that greatly improved model accuracy. Andrej Karpathy for example has praised our work.
Unsloth streamlines local training, inference, data, and deployment
Unsloth supports inference and training for 500+ models: vision, TTS, embedding, RL

⭐ Features

Unsloth lets you run and train models for text, audio, embedding, vision and more. Unsloth provides many key features for both inference and training:

Inference

Self-healing tool calling / web search and use Unsloth as an API.
Connect your local models to any agent: Claude Code, Codex, Hermes and more.
Search + download + run any model like GGUFs, LoRA adapters, safetensors.
Auto inference parameter tuning and edit chat templates.
Export or save your model to GGUF, 16-bit safetensor etc.
Compare outputs with two different model side by side.

Training

Train and RL 500+ models ~2x faster with ~70% less VRAM (no accuracy loss)
Supports full fine-tuning, pre-training, 4-bit, 16-bit and FP8 training.
Auto-create datasets from PDF, CSV, DOCX files. Edit data in a visual node workflow.
Observability: Monitor training live, track loss, GPU usage, customize graphs
Most efficient reinforcement learning library, using 80% less VRAM for GRPO, FP8 etc.
Multi-GPU works but a much better version is coming!