> For the complete documentation index, see [llms.txt](https://yvechat.gitbook.io/wp/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yvechat.gitbook.io/wp/getting-started/install-ollama.md).

# Install Ollama

Ollama serves language models on your computer. YveChat supports it as the primary local runtime.

***

### Install

Follow the official instructions for your operating system:

* [Ollama download page](https://ollama.com/download)
* [Ollama documentation](https://docs.ollama.com/)

The installer covers Windows, macOS, and Linux. Canonical instructions are maintained by Ollama, and this page links to them, because those steps change over time.

***

### Confirm it is running

Ollama listens on `127.0.0.1:11434` by default. Open that address in a browser. A short confirmation message indicates the service is running.

Source: [Ollama FAQ](https://docs.ollama.com/faq)

***

### How YveChat reaches Ollama

YveChat Engine connects to Ollama on your machine and presents the available models to the hosted interface. Ollama accepts cross-origin browser requests only from `127.0.0.1` and `0.0.0.0` by default, so YveChat Engine performs the connection locally.

Source: [Ollama FAQ](https://docs.ollama.com/faq)

{% hint style="info" %}
This arrangement means you do not configure `OLLAMA_ORIGINS` for normal YveChat use. Local Engine and Ollama run on the same machine and communicate over loopback.
{% endhint %}

***

### Other runtimes

| Runtime                     | Status       | Requirement                                    |
| --------------------------- | ------------ | ---------------------------------------------- |
| Ollama                      | Available    | Primary supported local language-model runtime |
| OpenAI-compatible endpoints | Experimental | Manual configuration                           |
| vLLM                        | Experimental | Manual configuration, and GPU infrastructure   |

vLLM installation targets CUDA and ROCm environments, which makes it suited to machines with dedicated GPU infrastructure.

Source: [vLLM GPU installation](https://docs.vllm.ai/en/stable/getting_started/installation/gpu/)

Experimental support may change between releases.

***

### Next

Continue to [Choose Your First Model](/wp/getting-started/choose-your-first-model.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://yvechat.gitbook.io/wp/getting-started/install-ollama.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.