> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/desktop.md).
# Introducing Unsloth Desktop
Introducing Unsloth Desktop
Unsloth Desktop (Beta) is a free, open-source app for running and training AI models on your own local hardware. Available for macOS, Windows, and Linux.
Unsloth lets you run, train and deploy LLMs, diffusion image/video, MLX, GGUF and audio models.
{% columns %}
{% column width="16.666666666666664%" %}
{% endcolumn %}
{% column width="66.66666666666667%" %}
{% stepper %}
{% step %}
### Install Unsloth Desktop
1. Download [Unsloth Desktop](https://unsloth.ai/download)
2. Install the app for [macOS](https://unsloth.ai/download/mac), [Windows](/docs/get-started/install/windows-installation.md), or [Linux](https://www.jan.ai/docs/desktop/install/linux)
3. Launch the app
{% endstep %}
{% step %}
### Choose a model
Open 'Select model' dropdown ontop or 'Model hub' tab, choose a model and a quantization that fits your device, then download it. Once it finishes, start chatting - no setup required.
{% endstep %}
{% step %}
### Unsloth is now ready
To chat, type a message and press Enter.
* **Connect tools:** [Claude Code](/docs/basics/claude-code.md), [Codex](/docs/basics/codex.md), [web search](/docs/new/studio/chat.md#advanced-web-search), [MCP](/docs/basics/mcp.md) and more
* **Train models:** Fine-tune text, diffusion, [embedding](/docs/basics/embedding-finetuning.md), and more
* **Generate media:** Create and train [images](/docs/basics/diffusion-image.md), video, [TTS](/docs/basics/text-to-speech-tts-fine-tuning.md) locally
{% endstep %}
{% endstepper %}
{% endcolumn %}
{% column width="16.666666666666657%" %}
{% endcolumn %}
{% endcolumns %}
Feature Deep Dive ⭐
See everything Unsloth Desktop has to offer:
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.666666666666664%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
## :image: **Image and Video Generation**
Create images with MiniMax-H3, FLUX, Z-Image and fine-tuned LoRA adapters. Generate video with Wan and LTX models.
Transform, inpaint, extend, upscale, reference and edit existing images.
{% endcolumn %}
{% column width="8.333333333333325%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.66666666666666%" %}
## :terminal: Code execution
Get up to 50% more accurate tool-calling with self-healing tool calls that detect, repair and retry failures automatically.
Execute Bash and Python in a secure sandbox so models can run code, test results and complete real tasks locally.
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column width="41.666666666666686%" %}
## :comment: Access model anywhere
Serve your local or Colab models over HTTPS through Unsloth's free [Cloudflare tunnel](/docs/basics/how-to-serve-local-llms-anywhere-secure-remote-access-with-cloudflare-and-unsloth.md). Check a run from **your phone**, your laptop, or anywhere else you happen to be.
Bind the app to your network with `-H 0.0.0.0`, or open a free Cloudflare tunnel for HTTPS:
{% endcolumn %}
{% column %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
## :image: Use the Latest models
You can run and train nearly every model, including upcoming ones. Expect Day Zero support for models like Qwen3.8, Gemma, Meta, NVIDIA, GLM, Gemma models and more. It's all thanks to llama.cpp and Hugging Face and we're also proud to contribute back to the ecosystem.
{% endcolumn %}
{% column width="49.99999999999999%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.666666666666664%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
## :magnifying-glass: Deep Research
Normal search utilises the web for its answers and happens while the model is still thinking.
Deep research plans first, searches for the best sources, then produces a detailed report with all citations.
{% endcolumn %}
{% column width="8.33333333333334%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
## :image: **Train Diffusion Models**
Train LoRA adapters for SDXL, FLUX.2, Qwen-Image and Z-Image on your own images. Caption them in Studio, pick a rank, and hit train.
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column width="41.66666666666666%" %}
## :flask: Train with no code
Drop in a PDF, CSV or JSON and go. LoRA, full fine-tuning, pretraining. All 2x faster, 70% less VRAM, no accuracy loss. Multi-GPU and latest models work.
Text, diffusion, [audio](/docs/basics/text-to-speech-tts-fine-tuning.md) and [image](/docs/basics/vision-fine-tuning.md) models are supported!
{% endcolumn %}
{% column width="8.333333333333353%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666666%" %}
## :microphone: Transcribe/generate audio
Generate, fine-tune or transcribe audio with Unsloth completely locally. Text-to-speech, speech-to-text, Whisper, Qwen3-ASR, you name it!
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column width="8.333333333333336%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% embed url="" %}
{% endcolumn %}
{% column width="41.66666666666666%" %}
## :cloud: Use Cloud Models
Run models from OpenAI, Anthropic, Ollama, llama.cpp, vLLM, and more.
Use the same Unsloth chat interface for local and cloud models with support for tool-calling, image gen, [prompt caching](https://sites.gitbook.com/preview/site_mXXTe/~/revisions/KsWgqmEjr66G4kYiZdG8#prompt-caching) to reduce token usage while preserving provider-native features like OpenAI’s [web search](https://sites.gitbook.com/preview/site_mXXTe/~/revisions/KsWgqmEjr66G4kYiZdG8#web-search-and-thinking) and [code execution](https://sites.gitbook.com/preview/site_mXXTe/~/revisions/KsWgqmEjr66G4kYiZdG8#code-execution).
{% endcolumn %}
{% column width="8.333333333333336%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666667%" valign="middle" %}
## :alien-8bit: Connect your Agent
[Unsloth Start](/docs/integrations/unsloth-start.md) lets you connect [Claude Code](/docs/basics/claude-code.md), [Codex](/docs/basics/codex.md) and other agents to local models via the `unsloth start` command.
Start Unsloth, load a model, open your project folder, and then run:
```bash
unsloth start claude
```
{% endcolumn %}
{% column width="49.99999999999997%" %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
## Frequently asked questions
{% endcolumn %}
{% column width="41.66666666666667%" %}
{% endcolumn %}
{% column %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="41.66666666666667%" %}
#### Do you collect my data?
No telemetry. Unsloth detects your GPU type and device so the app can know what works. The app can run entirely offline.
#### Can I use models I already downloaded?
Yes, they are found automatically. If yours are not you can specify your own custom folders.
#### Why is inference slower sometimes?
Web search, code execution and tool-call healing all cost time. Turn them off and speed should match any other llama.cpp app. Still slow? Open a GitHub issue.
{% endcolumn %}
{% column width="41.66666666666667%" %}
#### GPU only?
No. Unsloth works on a wide variety of CPU, Mac etc setups.
#### Does it support OpenAI-compatible APIs?
Yes. See the [API guide](/docs/basics/api.md). We also support connection to [Cloud models](/docs/integrations/connections.md) or other APIs like Anthropic or OpenAI.
#### What devices does Unsloth support?
Unsloth supports all OS including Mac, Windows, Linux and WSL and supports NVIDIA, Intel, AMD and Mac GPUs/CPUs. Older hardware however may not be well supported.
{% endcolumn %}
{% column %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column width="8.333333333333332%" %}
{% endcolumn %}
{% column width="83.33333333333333%" %}
A huge thank you to NVIDIA and Hugging Face for being part of our launch. Also thanks to all of our early beta testers for Unsloth Desktop, we truly appreciate your time and feedback. We’d also like to thank Jan for inspiration and llama.cpp, PyTorch, stablediffusion.cpp, and open model labs for providing the infrastructure that made Unsloth Desktop possible.
{% endcolumn %}
{% column width="8.333333333333321%" %}
{% endcolumn %}
{% endcolumns %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://unsloth.ai/docs/desktop.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.