phi-3.5-vision-ov

phi-3.5-vision-ov is an OpenVino int4 quantized version of phi-3.5-vision-ov, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

This is a vision-to-text model from the Microsoft phi-3.5 series and is a very high-quality innovative small model that accepts multi-modal inputs (image/video, text).

Model Description

• Developed by: Microsoft
• Quantized by: llmware
• Model type: phi-3.5
• Parameters: 3 billion
• Model Parent: Microsoft/Phi-3.5-vision-instruct
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Multimodal LLM
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website