name = "Llama-3.2-11B-Vision-Instruct"
description = "Open multimodal Llama model for image understanding, captioning, and visual QA"
family = "llama"
release_date = "2024-09-25"
last_updated = "2024-09-25"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2023-12"
open_weights = true

[limit]
context = 128_000
output = 4_096

[modalities]
input = ["text", "image"]
output = ["text"]

[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"