tensorblock/glm-4-9b-hf-GGUF

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

THUDM/glm-4-9b-hf - GGUF

This repo contains GGUF format model files for THUDM/glm-4-9b-hf.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Filename	Quant type	File Size	Description
glm-4-9b-hf-Q2_K.gguf	Q2_K	4.005 GB	smallest, significant quality loss - not recommended for most purposes
glm-4-9b-hf-Q3_K_S.gguf	Q3_K_S	4.591 GB	very small, high quality loss
glm-4-9b-hf-Q3_K_M.gguf	Q3_K_M	4.973 GB	very small, high quality loss
glm-4-9b-hf-Q3_K_L.gguf	Q3_K_L	5.195 GB	small, substantial quality loss
glm-4-9b-hf-Q4_0.gguf	Q4_0	5.459 GB	legacy; small, very high quality loss - prefer using Q3_K_M
glm-4-9b-hf-Q4_K_S.gguf	Q4_K_S	5.757 GB	small, greater quality loss
glm-4-9b-hf-Q4_K_M.gguf	Q4_K_M	6.165 GB	medium, balanced quality - recommended
glm-4-9b-hf-Q5_0.gguf	Q5_0	6.556 GB	legacy; medium, balanced quality - prefer using Q4_K_M
glm-4-9b-hf-Q5_K_S.gguf	Q5_K_S	6.696 GB	large, low quality loss - recommended
glm-4-9b-hf-Q5_K_M.gguf	Q5_K_M	7.050 GB	large, very low quality loss - recommended
glm-4-9b-hf-Q6_K.gguf	Q6_K	8.265 GB	very large, extremely low quality loss
glm-4-9b-hf-Q8_0.gguf	Q8_0	9.998 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/glm-4-9b-hf-GGUF --include "glm-4-9b-hf-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/glm-4-9b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'