# How to Run Stakpak with Local LLM Models Using Ollama

## What is Stakpak?

Stakpak is an open source agent that lives on your machines 24/7, keeps your apps running, and only pings when it needs a human.

### Install

```shell
curl -sSL https://stakpak.dev/install.sh | sh
```

or check [Install Stakpak](/docs/get-started/install-stakpak.md)

### Usage with Ollama

#### Quick setup

1. Download the ollama model.
2. Open your terminal and run stakpak config

```shell
stakpak config
```

3. Choose create new profile
4. Add profile name

```shell
ollama
```

6. Choose "Use my own Model"
7. Choose "bring your own model"
8. Enter provider name:

```shell
ollama
```

8. Enter the endpoint:

```shell
http://localhost:11434/v1
```

9. Enter the API Key

```shell
ollama
```

10. Add your model name for smart mode
11. Add your model name for eco mode
12. Press "y" to save config
13. Press "y" to open stakpak

#### NOTE:

1. To open Stakpak with the Ollama profile, all you have to do is open your terminal and write:

```shell
stakpak --profile ollama
```

### Recommended Models

* `qwen3-coder`
* `glm-4.7`
* `gpt-oss:120b`

Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud).


---

# 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://stakpak.gitbook.io/docs/tutorial/how-to-run-stakpak-with-local-llm-models-using-ollama.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.