Q4_K_M

The microsoft/phi-4-GGUF model, quantized to Q4_K_M and split into 5GB GGUF files.

The model has been split using llama-gguf-split (b9789) as follows:

llama-gguf-split --split-max-size 5G phi-4-Q4_K_M.gguf phi-4-Q4_K_M

GGUF

Model size

15B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for inference-snaps/phi-4-Q4_K_M-5GB

Base model

Quantized

Quantized

(2)

this model