phi-4-GGUF

An unchanged copy of Phi-4 14B GGUF files, kept here so the WorkOffline app can download them from one place, pinned to an exact revision and checked against SHA-256.

Original model: microsoft/phi-4
GGUF files from: microsoft/phi-4-gguf
Made by: Microsoft
Licence: MIT License. LICENSE is copied from https://huggingface.co/microsoft/phi-4-gguf/blob/6edc2ef6664b739a8e11e62f2672ff6afe0c15ac/LICENSE

File here	Copied from	Upstream revision	Size (bytes)	SHA-256
`phi-4-Q4_K_M.gguf`	`microsoft/phi-4-gguf/phi-4-Q4_K.gguf`	`6edc2ef6664b739a8e11e62f2672ff6afe0c15ac`	9053114560	`5652b9be0ea4ae2842130d04fe31bc869fcb99a2b7106c53b4e754a343fd688f`

The bytes are identical to the upstream files; only the file name may differ. All credit for the model goes to its authors (microsoft) and for the GGUF conversion to microsoft. Use of the files is governed by the original licence.

Downloads last month: 50

GGUF

Model size

15B params

Architecture

phi3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for WorkOffline/phi-4-GGUF

Base model

microsoft/phi-4

Quantized

(172)

this model