phi-4-mm-ov

phi-4-mm-ov is an OpenVino int4 quantized version of phi-4-mm, 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 4 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-4
• Parameters: 6 billion
• Model Parent: microsoft/Phi-4-multimodal-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