MetaLlama 3.2
Llama 3.2 11B Vision Instruct
The 11B vision release adds an image adapter to the Llama 3.1 text model.
What the release provides
Text and image input produce text output with 128K context. Image-and-text applications officially support English. The Llama 3.2 Community License applies.Llama 3.2 vision model card
How to use it well
Practical guidance. Ask for visible evidence when reading a chart or document. Retain the image crop used for each answer. Image understanding does not guarantee correct arithmetic, so calculate totals outside the model when exact values matter.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | meta-llama/Llama-3.2-11B-Vision-Instruct |