How to Fine-tune LLMs in VS Code with Unsloth

Prerequisites

To begin we will need to have:

• Installed VS Code. Git (for cloning the notebook repo) should be installed by default.

• A Google account (to authenticate with Colab)

• Recommended: the Jupyter extension in VS Code (most setups already have it)

Install the Colab extension in VS Code

1. Open Extensions in VS Code (Ctrl+Shift+X / Cmd+Shift+X)

2. Search for “Colab” and install the Google Colab extension

Open an Unsloth notebook

1. Clone the notebooks repository:

   Copy

   git clone https://github.com/unslothai/notebooks
   cd notebooks

2. Open your desired notebook. Unsloth supports most models including embedding, TTS. For example, we'll use Qwen3-4B RL: nb/Qwen3_(4B)-GRPO.ipynb

Select a kernel and choose Colab

In the notebook toolbar, click Select Kernel, then choose Colab

Add a new Colab server

After choosing Colab, you’ll see a dropdown with server options.

1. Click + Add New Colab Server

2. The first time, a browser window may open for Google authentication

   • Log in, grant access, then return to VS Code

Select GPU and name the server

1. Set Hardware accelerator to GPU

2. Choose a GPU type (for example T4, if available)

3. Give the server a name (anything you like)

Pick the Python kernel

Once connected to the Colab server, select the Python kernel that appears for that runtime (usually a Python 3 kernel).

Run the notebook

• Click Run All in the notebook toolbar (or run cells top-to-bottom)

• Watch the setup cells install dependencies and then start the Unsloth workflow