Llama Guard 3 11B Vision

A multimodal Meta safeguard model with 11B parameters: reads the prompt text and the image together and labels content safe or unsafe with the violated categories. The text side is optimized for English.

Llama Guard 4 предлагается как замена

Understands

text, images

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.