# How to Use Model Catalog?

Each model card includes:

* **Model Name** (e.g., `Qwen/Qwen3-14B`, `meta-llama/Llama-3-70B`)
* **Provider** (e.g., Qwen, Meta LLaMA, Google Gemma, DeepSeek, IBM Granite, Mistral)
* **Version or Size** (e.g., `7B`, `14B`, `70B`)

Each model card provides multiple options via the **three-dot menu (⋮)**:

* **Playground**

  Test the model directly in the Playground interface. You can interact with it before deployment.
* **Create API Endpoint**

  Generate an API endpoint for the model so it can be integrated into your applications or services.
* **Fine-tune**

  Customize the model using your own dataset to improve performance for your specific use case.

![file](https://fptcloud.com/wp-content/uploads/2025/09/image-1757045110043.png)

**Browsing and Searching Models**

* Use the **search bar** at the top to quickly find a model by name.
* Use the **filter tabs** (e.g., DeepSeek, GPT, Qwen, etc.) to view models from a specific family.
* At the bottom right, adjust the **“Models per page”** setting to display 8, 16,32, 64, or more models per page.
* Navigate between pages using the pagination controls.


---

# 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://ai-docs.fptcloud.com/fpt-ai-studio/services/model-hub/tutorials/how-to-use-model-catalog.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.