llama-11b-vision-instruct-ov

llama-11b-vision-instruct-ov is an OpenVino int4 quantized version of Llama 3.2 11B Vision Instruct, providing a small, fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

llama-11b-vision-instruct is a new 11B multi-modal instruct chat foundation model from Meta.

Model Description

• Developed by: meta-llama
• Quantized by: llmware
• Model type: llama-3.2
• Parameters: 11 billion
• Model Parent: meta-llama/Llama-3.2-11B-Vision-Instruct
• Language(s) (NLP): English
• License: Llama 3.2 Community License
• Uses: Multimodal (image+text -> text)
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

For a reference open source implementation, please see this Intel OpenVino Notebook

Model Card Contact

llmware on github

llmware on hf

llmware website