# Install Unsloth on MacOS

To install Unsloth locally on your local Apple MacOS device, follow the steps below:

### Install Unsloth

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

Use the same command to update or use `unsloth studio update`.

### Update Unsloth

```bash
unsloth studio update
```

### Launch

Every time you want to launch Unsloth again:

```bash
unsloth studio -H 0.0.0.0 -p 8888
```

For detailed Unsloth Studio install instructions and requirements, [view our guide](/docs/new/studio/install.md).

### Uninstall

To uninstall Unsloth Studio on macOs, follow these 4 steps:

#### **1. Remove the application**

* MacOS, Linux: `rm -rf ~/.unsloth/studio/unsloth_studio`

This removes the application but keeps your model checkpoints, exports, history, cache, and chats intact.

#### **2. Remove shortcuts and symlinks**

**macOS:**

```bash
rm -rf ~/Applications/Unsloth\ Studio.app ~/Desktop/Unsloth\ Studio
```

#### **3. Remove the CLI command**

**macOS, Linux:**

```bash
rm -f ~/.local/bin/unsloth
```

#### **4. Remove everything (optional)**

To also delete history, cache, chats, model checkpoints, and model exports, delete the entire Unsloth folder:

* MacOS, Linux: `rm -rf ~/.unsloth`

Note that downloaded HF model files are stored separately in the Hugging Face cache - none of the steps above will remove them. See **Deleting model files** below if you want to reclaim that disk space.

You can delete old model files either from the bin icon in model search or by removing the relevant cached model folder from the Hugging Face cache directory.

The default cache location is:

{% code expandable="true" %}

```bash
~/.cache/huggingface/hub/
```

{% endcode %}

If `HF_HUB_CACHE` or `HF_HOME` is set, use that location instead. On Linux and WSL, `XDG_CACHE_HOME` can also change the default cache root. You can check with:

{% code expandable="true" %}

```bash
echo ${HF_HUB_CACHE:-${HF_HOME:-${XDG_CACHE_HOME:-$HOME/.cache}/huggingface}/hub}
```

{% endcode %}

To delete a specific model, remove its folder (e.g. `models--unsloth--Llama-3.1-8B-bnb-4bit`) from the cache directory. To clear all cached models:

{% code expandable="true" %}

```bash
rm -rf ~/.cache/huggingface/hub/
```

{% endcode %}

**1. Remove the application**

MacOS, WSL, Linux: `rm -rf ~/.unsloth/studio/unsloth ~/.unsloth/studio/studio`

This removes the application but keeps your model checkpoints, exports, history, cache, and chats intact.

**2. Remove shortcuts and symlinks**

**macOS:**

```bash
rm -rf ~/Applications/Unsloth\ Studio.app ~/Desktop/Unsloth\ Studio
```

**Linux:**

```bash
rm -f ~/.local/share/applications/unsloth-studio.desktop ~/Desktop/unsloth-studio.desktop
```

**WSL:**

```bash
rm -f ~/Desktop/unsloth-studio.desktop
```

WSL also creates a Windows shortcut — open PowerShell and run:

```powershell
Remove-Item -Force "$HOME\Desktop\Unsloth Studio.lnk"
Remove-Item -Force "$env:APPDATA\Microsoft\Windows\Start Menu\Programs\Unsloth Studio.lnk"
```

**3. Remove the CLI command**

```bash
rm -f ~/.local/bin/unsloth
```

**4. Remove everything (optional)**

To also delete history, cache, chats, model checkpoints, and model exports:

```
rm -rf ~/.unsloth
```

Note that downloaded model files are stored separately in the Hugging Face cache — none of the steps above will remove them. See **Deleting model files** for how to reclaim that disk space.

### **Deleting model files**

You can delete old model files either from the bin icon in model search or by removing the relevant cached model folder from the Hugging Face cache directory.

The default cache location is:

```bash
~/.cache/huggingface/hub/
```

If `HF_HUB_CACHE` or `HF_HOME` is set, use that location instead. On Linux and WSL, `XDG_CACHE_HOME` can also change the default cache root. You can check with:

```bash
echo ${HF_HUB_CACHE:-${HF_HOME:-${XDG_CACHE_HOME:-$HOME/.cache}/huggingface}/hub}
```

To delete a specific model, remove its folder (e.g. `models--unsloth--Llama-3.1-8B-bnb-4bit`) from the cache directory. To clear all cached models:

```bash
rm -rf ~/.cache/huggingface/hub/
```


---

# Agent Instructions: 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:

```
GET https://unsloth.ai/docs/get-started/install/mac.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.