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

# 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.