> 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/choose-your-first-model.md).

# Choose Your First Model

A model is a file that Ollama downloads and loads into memory. The one you choose determines both the quality of the output and whether your machine copes.

***

### Start small

Downloading a small model first establishes that the whole path works: Ollama serves it, YveChat Engine finds it, and the workspace talks to it. A large model tests the same path while consuming far more time and disk.

| Situation                                           | Sensible starting point                      |
| --------------------------------------------------- | -------------------------------------------- |
| Testing the setup, or a machine with limited memory | A small model, roughly 1B to 3B parameters   |
| A modern machine with adequate memory               | A medium model, roughly 7B to 8B parameters  |
| Substantial memory and a capable GPU                | A larger model, once the small one is proven |

Browse available models on the [Ollama model library](https://ollama.com/library). Each entry lists its sizes and download footprint.

***

### Downloading a model

Models are pulled through Ollama. YveChat Engine can perform an approved pull on your behalf, and it reports progress while the download runs.

Downloads are large. A medium model commonly runs to several gigabytes, and a large model to tens of gigabytes. Each model you keep occupies that space until you remove it.

{% hint style="info" %}
The hosted browser interface never executes installation commands. YveChat Engine performs them on your machine after you confirm.
{% endhint %}

***

### Newly installed models

Model discovery is dynamic. A model installed through Ollama appears in the workspace after a refresh, without reinstalling or reconfiguring anything.

Use the refresh control under the model selector when a newly pulled model has yet to appear.

***

### Image models

Image generation uses a separate path. Language models come from Ollama. Image models come from ComfyUI, presented through a dynamic capability-aware image registry, and they appear in Image Studio. The language model selector lists Ollama models alone.

Installing a language model therefore has no effect on the image model list, and the reverse holds too.

***

### Capability filters

Models differ in what they can do. The selector filters by capability, so a model that handles images is distinguishable from one that handles text alone.

Choosing a model that lacks a capability you need produces poor results, and the filter exists to make the difference visible before you start.

***

### Next

Continue to [Pair Your Browser](/wp/getting-started/pair-your-browser.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/choose-your-first-model.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.