tensorblock/gemma-2-9b-it-GGUF

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

google/gemma-2-9b-it - GGUF

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

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

<bos><start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model

Filename	Quant type	File Size	Description
gemma-2-9b-it-Q2_K.gguf	Q2_K	3.805 GB	smallest, significant quality loss - not recommended for most purposes
gemma-2-9b-it-Q3_K_S.gguf	Q3_K_S	4.338 GB	very small, high quality loss
gemma-2-9b-it-Q3_K_M.gguf	Q3_K_M	4.762 GB	very small, high quality loss
gemma-2-9b-it-Q3_K_L.gguf	Q3_K_L	5.132 GB	small, substantial quality loss
gemma-2-9b-it-Q4_0.gguf	Q4_0	5.443 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gemma-2-9b-it-Q4_K_S.gguf	Q4_K_S	5.479 GB	small, greater quality loss
gemma-2-9b-it-Q4_K_M.gguf	Q4_K_M	5.761 GB	medium, balanced quality - recommended
gemma-2-9b-it-Q5_0.gguf	Q5_0	6.484 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gemma-2-9b-it-Q5_K_S.gguf	Q5_K_S	6.484 GB	large, low quality loss - recommended
gemma-2-9b-it-Q5_K_M.gguf	Q5_K_M	6.647 GB	large, very low quality loss - recommended
gemma-2-9b-it-Q6_K.gguf	Q6_K	7.589 GB	very large, extremely low quality loss
gemma-2-9b-it-Q8_0.gguf	Q8_0	9.827 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/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-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-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'