# Choosing the right model

## Cloud-Based Models

LLM Vision is compatible with multiple providers, each of which has different models available. Some providers run in the cloud, while others are self-hosted.\
To see which model is best for your use case, check the figure below. It visualizes the averaged [MMMU ](#user-content-fn-1)[^1]scores of available cloud-based models. The higher the score, the more accurate the output.

{% hint style="info" %}
**`gpt-5-mini`** is the recommended model due to its strong performance-to-price ratio.
{% endhint %}

<figure><img src="/files/KFghVKBbp1xCTd5dyVM5" alt=""><figcaption><p>Data is based on the <a href="https://mmmu-benchmark.github.io/#leaderboard">MMMU Leaderboard</a></p></figcaption></figure>

## Self-hosted Models

{% hint style="info" %}
**`gemma3:12b`** is the recommended model for self-hosting, offering performance comparable to `gpt-4o-mini` while fitting within 12GB of VRAM.
{% endhint %}

<figure><img src="/files/hesi9xqKURZYArZbapU9" alt=""><figcaption><p>Data is based on the <a href="https://mmmu-benchmark.github.io/#leaderboard">MMMU Leaderboard</a></p></figcaption></figure>

[^1]: MMMU stands for "Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark". It assesses multimodal capabilities including image understanding.


---

# 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://llmvision.gitbook.io/getting-started/choosing-the-right-model.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.