tensorblock/SOLAR-KOEN-10.8B-GGUF

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

beomi/SOLAR-KOEN-10.8B - GGUF

This repo contains GGUF format model files for beomi/SOLAR-KOEN-10.8B.

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

Filename	Quant type	File Size	Description
SOLAR-KOEN-10.8B-Q2_K.gguf	Q2_K	3.791 GB	smallest, significant quality loss - not recommended for most purposes
SOLAR-KOEN-10.8B-Q3_K_S.gguf	Q3_K_S	4.413 GB	very small, high quality loss
SOLAR-KOEN-10.8B-Q3_K_M.gguf	Q3_K_M	4.908 GB	very small, high quality loss
SOLAR-KOEN-10.8B-Q3_K_L.gguf	Q3_K_L	5.331 GB	small, substantial quality loss
SOLAR-KOEN-10.8B-Q4_0.gguf	Q4_0	5.731 GB	legacy; small, very high quality loss - prefer using Q3_K_M
SOLAR-KOEN-10.8B-Q4_K_S.gguf	Q4_K_S	5.774 GB	small, greater quality loss
SOLAR-KOEN-10.8B-Q4_K_M.gguf	Q4_K_M	6.094 GB	medium, balanced quality - recommended
SOLAR-KOEN-10.8B-Q5_0.gguf	Q5_0	6.972 GB	legacy; medium, balanced quality - prefer using Q4_K_M
SOLAR-KOEN-10.8B-Q5_K_S.gguf	Q5_K_S	6.972 GB	large, low quality loss - recommended
SOLAR-KOEN-10.8B-Q5_K_M.gguf	Q5_K_M	7.159 GB	large, very low quality loss - recommended
SOLAR-KOEN-10.8B-Q6_K.gguf	Q6_K	8.291 GB	very large, extremely low quality loss
SOLAR-KOEN-10.8B-Q8_0.gguf	Q8_0	10.737 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/SOLAR-KOEN-10.8B-GGUF --include "SOLAR-KOEN-10.8B-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/SOLAR-KOEN-10.8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'