Skip to content

Llama-3.2-11B-Vision

A multimodal model that handles images and text

Visit official site

What Llama-3.2-11B-Vision is

The model is described as a Meta multimodal LLM that combines image and text processing for visual tasks.

What you can do with it

  • Combine an image with a text prompt
  • Retrieve text matching an uploaded image

Pros & cons

✓ What we like

  • DocVQA support is listed
  • Text tasks name several languages

! What to watch out for

  • Image plus text use is described as English only
  • Use follows the Llama 3.2 community license

FAQ

Who released it?

The material names Meta.

Can it read documents?

DocVQA is listed, where the model reads text and layout.

Last reviewed: 2026-11-15

More AI image generation tools

View all →

How we review