tensorblock/MistralTrix8x9B-GGUF

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

Kquant03/MistralTrix8x9B - GGUF

This repo contains GGUF format model files for Kquant03/MistralTrix8x9B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Filename	Quant type	File Size	Description
MistralTrix8x9B-Q2_K.gguf	Q2_K	21.601 GB	smallest, significant quality loss - not recommended for most purposes
MistralTrix8x9B-Q3_K_S.gguf	Q3_K_S	25.500 GB	very small, high quality loss
MistralTrix8x9B-Q3_K_M.gguf	Q3_K_M	28.113 GB	very small, high quality loss
MistralTrix8x9B-Q3_K_L.gguf	Q3_K_L	30.171 GB	small, substantial quality loss
MistralTrix8x9B-Q4_0.gguf	Q4_0	33.009 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MistralTrix8x9B-Q4_K_S.gguf	Q4_K_S	33.386 GB	small, greater quality loss
MistralTrix8x9B-Q4_K_M.gguf	Q4_K_M	35.515 GB	medium, balanced quality - recommended
MistralTrix8x9B-Q5_0.gguf	Q5_0	40.240 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MistralTrix8x9B-Q5_K_S.gguf	Q5_K_S	40.240 GB	large, low quality loss - recommended
MistralTrix8x9B-Q5_K_M.gguf	Q5_K_M	41.487 GB	large, very low quality loss - recommended
MistralTrix8x9B-Q6_K.gguf	Q6_K	47.922 GB	very large, extremely low quality loss
MistralTrix8x9B-Q8_0	Q8_0	4.228 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/MistralTrix8x9B-GGUF --include "MistralTrix8x9B-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/MistralTrix8x9B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'