Llama 3.2 Vision 11B

Good fit for

People seeking an image-capable Llama rather than the text-only 3B or 8B models already listed.

Why consider it

The exact entry documents text-plus-image input and text output, with a working local API image example.

Main limitations

English is the only officially supported language for image-plus-text applications; eight supported text-only languages do not imply equivalent multilingual vision support. This does not generate images. Check license eligibility and deployment restrictions before use.

Cost and access

No subscription or per-token hosted fee for local inference within permitted uses. Hardware, electricity and setup are separate. Llama 3.2 Community License Agreement and Acceptable Use Policy apply. Review the multimodal terms for your location and deployment.

Getting started

Install a current compatible Ollama version, review the exact license and run: ollama run llama3.2-vision:11b. API refers to the local runtime endpoint, not a hosted API included with the weights.