tensorblock/SOLARC-MOE-10.7Bx6-GGUF

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

DopeorNope/SOLARC-MOE-10.7Bx6 - GGUF

This repo contains GGUF format model files for DopeorNope/SOLARC-MOE-10.7Bx6.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

### System:
{system_prompt}

### User:
{prompt}

### Assistant:

Filename	Quant type	File Size	Description
SOLARC-MOE-10.7Bx6-Q2_K.gguf	Q2_K	19.312 GB	smallest, significant quality loss - not recommended for most purposes
SOLARC-MOE-10.7Bx6-Q3_K_S.gguf	Q3_K_S	22.836 GB	very small, high quality loss
SOLARC-MOE-10.7Bx6-Q3_K_M.gguf	Q3_K_M	25.349 GB	very small, high quality loss
SOLARC-MOE-10.7Bx6-Q3_K_L.gguf	Q3_K_L	27.455 GB	small, substantial quality loss
SOLARC-MOE-10.7Bx6-Q4_0.gguf	Q4_0	29.859 GB	legacy; small, very high quality loss - prefer using Q3_K_M
SOLARC-MOE-10.7Bx6-Q4_K_S.gguf	Q4_K_S	30.125 GB	small, greater quality loss
SOLARC-MOE-10.7Bx6-Q4_K_M.gguf	Q4_K_M	32.065 GB	medium, balanced quality - recommended
SOLARC-MOE-10.7Bx6-Q5_0.gguf	Q5_0	36.469 GB	legacy; medium, balanced quality - prefer using Q4_K_M
SOLARC-MOE-10.7Bx6-Q5_K_S.gguf	Q5_K_S	36.469 GB	large, low quality loss - recommended
SOLARC-MOE-10.7Bx6-Q5_K_M.gguf	Q5_K_M	37.605 GB	large, very low quality loss - recommended
SOLARC-MOE-10.7Bx6-Q6_K.gguf	Q6_K	43.492 GB	very large, extremely low quality loss
SOLARC-MOE-10.7Bx6-Q8_0	Q8_0	56.330 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/SOLARC-MOE-10.7Bx6-GGUF --include "SOLARC-MOE-10.7Bx6-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/SOLARC-MOE-10.7Bx6-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'