tensorblock/Cydonia-24B-v2-GGUF

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

TheDrummer/Cydonia-24B-v2 - GGUF

This repo contains GGUF format model files for TheDrummer/Cydonia-24B-v2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.

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

Filename	Quant type	File Size	Description
Cydonia-24B-v2-Q2_K.gguf	Q2_K	8.890 GB	smallest, significant quality loss - not recommended for most purposes
Cydonia-24B-v2-Q3_K_S.gguf	Q3_K_S	10.400 GB	very small, high quality loss
Cydonia-24B-v2-Q3_K_M.gguf	Q3_K_M	11.474 GB	very small, high quality loss
Cydonia-24B-v2-Q3_K_L.gguf	Q3_K_L	12.401 GB	small, substantial quality loss
Cydonia-24B-v2-Q4_0.gguf	Q4_0	13.442 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Cydonia-24B-v2-Q4_K_S.gguf	Q4_K_S	13.549 GB	small, greater quality loss
Cydonia-24B-v2-Q4_K_M.gguf	Q4_K_M	14.334 GB	medium, balanced quality - recommended
Cydonia-24B-v2-Q5_0.gguf	Q5_0	16.304 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Cydonia-24B-v2-Q5_K_S.gguf	Q5_K_S	16.304 GB	large, low quality loss - recommended
Cydonia-24B-v2-Q5_K_M.gguf	Q5_K_M	16.764 GB	large, very low quality loss - recommended
Cydonia-24B-v2-Q6_K.gguf	Q6_K	19.346 GB	very large, extremely low quality loss
Cydonia-24B-v2-Q8_0.gguf	Q8_0	25.055 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/Cydonia-24B-v2-GGUF --include "Cydonia-24B-v2-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/Cydonia-24B-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'