tensorblock/solar_merge_test_1-GGUF

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

jieunhan/solar_merge_test_1 - GGUF

This repo contains GGUF format model files for jieunhan/solar_merge_test_1.

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_merge_test_1-Q2_K.gguf	Q2_K	6.645 GB	smallest, significant quality loss - not recommended for most purposes
solar_merge_test_1-Q3_K_S.gguf	Q3_K_S	7.799 GB	very small, high quality loss
solar_merge_test_1-Q3_K_M.gguf	Q3_K_M	8.663 GB	very small, high quality loss
solar_merge_test_1-Q3_K_L.gguf	Q3_K_L	9.395 GB	small, substantial quality loss
solar_merge_test_1-Q4_0.gguf	Q4_0	10.164 GB	legacy; small, very high quality loss - prefer using Q3_K_M
solar_merge_test_1-Q4_K_S.gguf	Q4_K_S	10.248 GB	small, greater quality loss
solar_merge_test_1-Q4_K_M.gguf	Q4_K_M	10.865 GB	medium, balanced quality - recommended
solar_merge_test_1-Q5_0.gguf	Q5_0	12.389 GB	legacy; medium, balanced quality - prefer using Q4_K_M
solar_merge_test_1-Q5_K_S.gguf	Q5_K_S	12.389 GB	large, low quality loss - recommended
solar_merge_test_1-Q5_K_M.gguf	Q5_K_M	12.750 GB	large, very low quality loss - recommended
solar_merge_test_1-Q6_K.gguf	Q6_K	14.754 GB	very large, extremely low quality loss
solar_merge_test_1-Q8_0.gguf	Q8_0	19.108 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_merge_test_1-GGUF --include "solar_merge_test_1-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_merge_test_1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'