# Unsloth Studio

> App for running, chatting with and training AI models locally

- Category: Agents & dev (`agents`)
- Tags: `free`, `open-source`
- Official: https://unsloth.ai/docs/new/changelog
- Wunderlust: https://wunderlust.xyz/r/unsloth-studio
- Image: https://wunderlust.xyz/media/unsloth-studio-poster.jpg
- Video preview: https://wunderlust.xyz/media/unsloth-studio.webm
- Added: 2026-11-05

## What it is

Unsloth's interface for running and training AI models on your own machine, available as a desktop app for macOS, Windows and Linux.

## What it’s for

For anyone who wants to test and fine-tune local models (chat, RAG, training and export) without depending on cloud services.

## Benefits

- Local chat with GGUF and MLX models, with tool calls, web search and code execution
- Model training and export, including to GGUF
- OpenAI-compatible API for connecting tools like Claude Code and Codex
- Chat with your own files (RAG) and project-based organization

## Caveats

- The page calls the app open source but doesn't state a license or price
- The identification as Unsloth Studio is a likely match based on name and description

## Similar on Wunderlust

- [Ollama](https://wunderlust.xyz/r/ollama.md): Runtime for running language models on your own machine
- [MLX](https://wunderlust.xyz/r/mlx.md): Stack for running local models on Macs
- [OpenClaw](https://wunderlust.xyz/r/openclaw.md): Open-source AI assistant that runs on your machine and replies through chat apps
- [Aurelio](https://wunderlust.xyz/r/aurelio-finance.md): Open source wealth and financial-planning app that runs on your own computer
- [LightRAG](https://wunderlust.xyz/r/lightrag.md): A RAG framework with a knowledge graph and embeddings
- [Autoresearch (Karpathy)](https://wunderlust.xyz/r/autoresearch.md): Karpathy's loop where an agent edits training, measures, and keeps or discards