llama.cpp support when?

#7
by alanzhuly - opened

Great model and use case. I want to try locally on Mac!

Microsoft org

Thank you for your interest in the Phi-4-multimodal!
Our Huggingface friend has just shared that the model can run with llama.cpp

All you need is:

brew install llama.cpp

Followed by:

llama-cli -hf bartowski/microsoft_Phi-4-mini-instruct-GGUF:Q8_0

That's another one model. Not multimodal.

Sign up or log in to comment