# LM Studio

LM Studio is a desktop app that lets you run powerful AI language models directly on your own computer—no internet or cloud required. With a clean, user-friendly interface, you can easily download models, chat with them, and tweak how they behave. It’s a great way to explore AI hands-on while keeping full control over your data and privacy.

{% stepper %}
{% step %}

### Install LM Studio

Download and install [LM Studio](https://lmstudio.ai/) on your PC.
{% endstep %}

{% step %}

### Install LLM models

To use LM Studio, you first need to download an LLM model. For compatibility with Robpod AI CoWorker, the selected model must support tool-calling functionality.

Here you can find a couple of models that works great:

| **Qwen2.5-7B**  | <a href="https://model.lmstudio.ai/download/lmstudio-community/Qwen2.5-7B-Instruct-GGUF" class="button primary">Install Model</a> | Small and fast model                                |
| --------------- | --------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------- |
| **gpt-oss-20b** | <a href="https://model.lmstudio.ai/download/openai/gpt-oss-20bopenai/gpt-oss-20b" class="button primary">Install Model</a>        | Bigger and more advanced model provided by Open AI. |
| {% endstep %}   |                                                                                                                                   |                                                     |

{% step %}

### Setup AI CoWorker

Open [Robpod AI CoWorker](/ai-coworker/introduction.md) on your PC.&#x20;

Select **LM Studio** as AI provider.&#x20;

To automatically setup Robpod connector for LM Studio click **... → Auto Config.** This will connect Robpod AI CoWorker with LM studio.&#x20;

Otherwise follow [step 4](/ai-coworker/setup/lm-studio.md#add-robpod-connector-to-lm-studio) to manually configure the connector.

Click on **CONNECT**.

<figure><img src="/files/yEtbw4g0LXC3l3h7LgjF" alt="" width="232"><figcaption></figcaption></figure>
{% endstep %}

{% step %}

### Add Robpod Connector to LM Studio (Manual Setup)

{% hint style="info" %}
Follow this step only if you need to manually setup the connector. If you have use the Auto Config option you can skip this step.
{% endhint %}

Click on  **Show Settings → Program → Integrations → Edit mcp.json**

The setup file for MCP connectors will open. Add the connector as follow:

```json
{
   "mcpServers":{
      "robpod-coworker":{
         "url":"http://127.0.0.1:29696/mcp",
         "timeout":120000
      }
   }
}
```

{% endstep %}

{% step %}

### Chat with LM Studio

If connector is created successfully, you can start chating with the AI assisant.
{% endstep %}
{% endstepper %}

{% embed url="<https://youtu.be/1heAXuAi0kQ>" %}


---

# 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://docs.robpod.cloud/ai-coworker/setup/lm-studio.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.