Model Details

GGUF build of Microsoft-Phi-4-14.7B model

GGUF

Model size

14.7B params

Architecture

phi3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for doaonduty/phi-4-q8_0.gguf

Base model

microsoft/phi-4

Quantized

(136)

this model