# Supported local Ollama models with Cody

{/* Internal docs only. Offloading from our production docs for now. */}

<Callout type="info">
	Compatibility with Ollama is currently in the Experimental stage and is
	available for Cody Free and Pro plans. The support is for Ollama is limited
	feel free to contact us for any questions or feedback.
</Callout>

## Cody Autocomplete with Ollama

To get autocomplete suggestions from Ollama locally, follow these steps:

- Install and run [Ollama](https://ollama.ai/)
- Download one of the supported local models using `pull`. The `pull` command is used to download models from the Ollama library to your local machine.
    - `ollama pull deepseek-coder-v2` for [deepseek-coder](https://ollama.com/library/deepseek-coder-v2)
    - `ollama pull codellama:13b` for [codellama](https://ollama.ai/library/codellama)
    - `ollama pull starcoder2:7b` for [starcoder2](https://ollama.ai/library/starcoder2)
- Update Cody's VS Code settings to use the `experimental-ollama` autocomplete provider and configure the right model:

```json
"cody.autocomplete.advanced.provider": "experimental-ollama",
"cody.autocomplete.experimental.ollamaOptions": {
    "url": "http://localhost:11434",
    "model": "deepseek-coder-v2"
}
```

- Confirm Cody uses Ollama by looking at the Cody output channel or the autocomplete trace view (in the command palette)

## Cody chat with Ollama

![Chat model selector](https://storage.googleapis.com/sourcegraph-assets/Docs/local-ollama-2025.jpg)

To generate chat with Ollama locally, follow these steps:

- Download [Ollama](https://ollama.com/download)
- Start Ollama (make sure the Ollama logo is showing up in your menu bar)
- Select a chat model (model that includes instruct or chat, for example, [gemma:7b-instruct-q4_K_M](https://ollama.com/library/gemma:7b-instruct-q4_K_M)) from the [Ollama Library](https://ollama.com/library)
- Pull (download) the chat model locally (for example, `ollama pull gemma:7b-instruct-q4_K_M`)
- Once the chat model is downloaded successfully, open Cody in VS Code
- Open a new Cody chat
- In the new chat panel, you should see the chat model you've pulled in the dropdown list
- Currently, you will need to restart VS Code to see the new models

<Callout type="note">
	You can run `ollama list` in your terminal to see what models are currently
	available on your machine.
</Callout>

### Run Cody offline with local Ollama models

You can use Cody with or without an internet connection. The offline mode does not require you to sign in with your Sourcegraph account to use Ollama. Click the button below the Ollama logo and you'll be ready to go.

![offline-cody-with-ollama](https://storage.googleapis.com/sourcegraph-assets/Docs/cody-offline-ollama.jpg)

You still have the option to switch to your Sourcegraph account whenever you want to use Claude, OpenAI, Gemini, etc.