Hugging Face · #167

meta-llama/Llama-3.2-11B-Vision-Instruct

meta-llama/Llama-3.2-11B-Vision-Instruct is a 10.7B image-text-to-text model on Hugging Face. Run locally: llama-cli -hf meta-llama/Llama-3.2-11B-Vision-Instruct or ollama run hf.co/meta-llama/Llama-3.2-11B-Vision-Instruct. 1,679 Hugging Face likes (#167 in this directory).

Model
https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
Author
meta-llama (org)
Likes
1,679
Downloads (30 days)
60,718
Task
image-text-to-text
Library
transformers
License
llama3.2
Parameters
10.7B
Gated
Access requires accepting terms on Hugging Face
Created
2024-09-18
Last modified
2024-12-04
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf meta-llama/Llama-3.2-11B-Vision-Instruct

Ollama

ollama run hf.co/meta-llama/Llama-3.2-11B-Vision-Instruct

This model is gated. Accept the terms on the Hugging Face card first. llama-cli -hf and ollama run hf.co/... then download a published GGUF; they do not skip Hub access checks.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run meta-llama/Llama-3.2-11B-Vision-Instruct only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology