Phi-4-GGUF

Original Model

microsoft/phi-4

Run with Gaianet

Prompt template:

prompt template: phi-4-chat

Context size:

chat_ctx_size: 16000

Run with GaiaNet:

Quantized with llama.cpp b4450

Downloads last month
955
GGUF
Model size
14.7B params
Architecture
phi3

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for gaianet/phi-4-GGUF

Base model

microsoft/phi-4
Quantized
(88)
this model