tensorblock/TestMixtral-GGUF

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

artek0chumak/TestMixtral - GGUF

This repo contains GGUF format model files for artek0chumak/TestMixtral.

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
TestMixtral-Q2_K.gguf	Q2_K	0.005 GB	smallest, significant quality loss - not recommended for most purposes
TestMixtral-Q3_K_S.gguf	Q3_K_S	0.005 GB	very small, high quality loss
TestMixtral-Q3_K_M.gguf	Q3_K_M	0.005 GB	very small, high quality loss
TestMixtral-Q3_K_L.gguf	Q3_K_L	0.005 GB	small, substantial quality loss
TestMixtral-Q4_0.gguf	Q4_0	0.005 GB	legacy; small, very high quality loss - prefer using Q3_K_M
TestMixtral-Q4_K_S.gguf	Q4_K_S	0.006 GB	small, greater quality loss
TestMixtral-Q4_K_M.gguf	Q4_K_M	0.006 GB	medium, balanced quality - recommended
TestMixtral-Q5_0.gguf	Q5_0	0.006 GB	legacy; medium, balanced quality - prefer using Q4_K_M
TestMixtral-Q5_K_S.gguf	Q5_K_S	0.006 GB	large, low quality loss - recommended
TestMixtral-Q5_K_M.gguf	Q5_K_M	0.006 GB	large, very low quality loss - recommended
TestMixtral-Q6_K.gguf	Q6_K	0.007 GB	very large, extremely low quality loss
TestMixtral-Q8_0.gguf	Q8_0	0.007 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/TestMixtral-GGUF --include "TestMixtral-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/TestMixtral-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'