tensorblock/phi-2-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

microsoft/phi-2 - GGUF

This repo contains GGUF format model files for microsoft/phi-2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

Model file specification

Filename	Quant type	File Size	Description
phi-2-Q2_K.gguf	Q2_K	1.034 GB	smallest, significant quality loss - not recommended for most purposes
phi-2-Q3_K_S.gguf	Q3_K_S	1.165 GB	very small, high quality loss
phi-2-Q3_K_M.gguf	Q3_K_M	1.328 GB	very small, high quality loss
phi-2-Q3_K_L.gguf	Q3_K_L	1.467 GB	small, substantial quality loss
phi-2-Q4_0.gguf	Q4_0	1.492 GB	legacy; small, very high quality loss - prefer using Q3_K_M
phi-2-Q4_K_S.gguf	Q4_K_S	1.508 GB	small, greater quality loss
phi-2-Q4_K_M.gguf	Q4_K_M	1.618 GB	medium, balanced quality - recommended
phi-2-Q5_0.gguf	Q5_0	1.801 GB	legacy; medium, balanced quality - prefer using Q4_K_M
phi-2-Q5_K_S.gguf	Q5_K_S	1.801 GB	large, low quality loss - recommended
phi-2-Q5_K_M.gguf	Q5_K_M	1.865 GB	large, very low quality loss - recommended
phi-2-Q6_K.gguf	Q6_K	2.128 GB	very large, extremely low quality loss
phi-2-Q8_0.gguf	Q8_0	2.755 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/phi-2-GGUF --include "phi-2-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/phi-2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'