> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openinterpreter.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LM Studio

Open Interpreter can use OpenAI-compatible server to run models locally. (LM Studio, jan.ai, ollama etc)

Simply run `interpreter` with the api\_base URL of your inference server (for LM studio it is `http://localhost:1234/v1` by default):

```shell theme={null}
interpreter --api_base "http://localhost:1234/v1" --api_key "fake_key"
```

Alternatively you can use Llamafile without installing any third party software just by running

```shell theme={null}
interpreter --local
```

for a more detailed guide check out [this video by Mike Bird](https://www.youtube.com/watch?v=CEs51hGWuGU?si=cN7f6QhfT4edfG5H)

**How to run LM Studio in the background.**

1. Download [https://lmstudio.ai/](https://lmstudio.ai/) then start it.
2. Select a model then click **↓ Download**.
3. Click the **↔️** button on the left (below 💬).
4. Select your model at the top, then click **Start Server**.

Once the server is running, you can begin your conversation with Open Interpreter.

(When you run the command `interpreter --local` and select LMStudio, these steps will be displayed.)

<Info>
  Local mode sets your `context_window` to 3000, and your `max_tokens` to 1000.
  If your model has different requirements, [set these parameters
  manually.](/settings#language-model)
</Info>

# Python

Compared to the terminal interface, our Python package gives you more granular control over each setting.

You can point `interpreter.llm.api_base` at any OpenAI compatible server (including one running locally).

For example, to connect to [LM Studio](https://lmstudio.ai/), use these settings:

```python theme={null}
from interpreter import interpreter

interpreter.offline = True # Disables online features like Open Procedures
interpreter.llm.model = "openai/x" # Tells OI to send messages in OpenAI's format
interpreter.llm.api_key = "fake_key" # LiteLLM, which we use to talk to LM Studio, requires this
interpreter.llm.api_base = "http://localhost:1234/v1" # Point this at any OpenAI compatible server

interpreter.chat()
```

Simply ensure that **LM Studio**, or any other OpenAI compatible server, is running at `api_base`.