Introducing Unsloth Desktop | Unsloth Documentation

Install Unsloth Desktop

Choose a model

Open 'Select model' dropdown on top 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.

Unsloth is now ready

To chat, type a message and press Enter.

• Train models: Fine-tune text, diffusion, embedding, and more

• Generate media: Create and train images, video, TTS locally

Control permissions

Unsloth, like Claude Code and Codex, provides permission controls for any model that uses tool calls. This means the model and Unsloth cannot access, modify, or edit your files or use the internet without your approval.

You can choose the level of access you want: Unsloth can run tools inside a secure sandbox environment to protect your system, or, if you prefer, you can allow it to directly access and edit your files.

Any Endpoint. Every Tool.

Unsloth removes the barrier between your inference setup and your workflow. Whether your model is running through Unsloth’s inference or your own remote OpenAI-compatible endpoint, you can give it access to Unsloth’s full suite of tools, including web search, code execution, deep research, and more.

Access model anywhere

Serve your local or over HTTPS through Unsloth's free Cloudflare tunnel. 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.

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. Unsloth offers more reliable call termination to reduce loops, better healing and deduplication to prevent XML leakage.

Serve on your local network

Put Unsloth on your Wi-Fi or wired network and serve the Unlosth over LAN. Traffic never leaves your network, so latency is low, and it works with no internet at all.

Press Start on the LAN access card, or launch with -H 0.0.0.0.

Image and Video Generation

For MiniMax-H3 FP8 on an NVIDIA B200, a 960×544, 124-frame, 8-step generation dropped from 70+ seconds to 13 seconds. Generate with FLUX, Z-Image, LTX, Wan and fine-tuned LoRA adapters.

Transform, inpaint, extend, upscale, reference and edit existing images.

Serve models via API

You can use unsloth run command and serve models like Qwen3.8 and change any settings, including context sizing, GPU layers, threading, sampling, networking, and tool configuration. For more info see our API docs.

See an example of using Unsloth API with Qwen3.8:

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.

Train Diffusion Models

Train LoRA adapters for SDXL, FLUX.2, Qwen-Image and Z-Image on your own images. Caption them in Unsloth, pick a rank, and hit train. Then you can export it and load the model back in Unsloth for inference.

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 and image models are supported!

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!

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.

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. We also support connection to Cloud models 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.