tensorblock/gemma-2-9b-GGUF

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

unsloth/gemma-2-9b - GGUF

This repo contains GGUF format model files for unsloth/gemma-2-9b.

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
gemma-2-9b-Q2_K.gguf	Q2_K	3.544 GB	smallest, significant quality loss - not recommended for most purposes
gemma-2-9b-Q3_K_S.gguf	Q3_K_S	4.040 GB	very small, high quality loss
gemma-2-9b-Q3_K_M.gguf	Q3_K_M	4.435 GB	very small, high quality loss
gemma-2-9b-Q3_K_L.gguf	Q3_K_L	4.780 GB	small, substantial quality loss
gemma-2-9b-Q4_0.gguf	Q4_0	5.069 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gemma-2-9b-Q4_K_S.gguf	Q4_K_S	5.103 GB	small, greater quality loss
gemma-2-9b-Q4_K_M.gguf	Q4_K_M	5.365 GB	medium, balanced quality - recommended
gemma-2-9b-Q5_0.gguf	Q5_0	6.038 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gemma-2-9b-Q5_K_S.gguf	Q5_K_S	6.038 GB	large, low quality loss - recommended
gemma-2-9b-Q5_K_M.gguf	Q5_K_M	6.191 GB	large, very low quality loss - recommended
gemma-2-9b-Q6_K.gguf	Q6_K	7.068 GB	very large, extremely low quality loss
gemma-2-9b-Q8_0.gguf	Q8_0	9.152 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/gemma-2-9b-GGUF --include "gemma-2-9b-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/gemma-2-9b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'