tensorblock/Iambe-20b-DARE-v2-GGUF

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

athirdpath/Iambe-20b-DARE-v2 - GGUF

This repo contains GGUF format model files for athirdpath/Iambe-20b-DARE-v2.

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

Filename	Quant type	File Size	Description
Iambe-20b-DARE-v2-Q2_K.gguf	Q2_K	7.420 GB	smallest, significant quality loss - not recommended for most purposes
Iambe-20b-DARE-v2-Q3_K_S.gguf	Q3_K_S	8.658 GB	very small, high quality loss
Iambe-20b-DARE-v2-Q3_K_M.gguf	Q3_K_M	9.706 GB	very small, high quality loss
Iambe-20b-DARE-v2-Q3_K_L.gguf	Q3_K_L	10.628 GB	small, substantial quality loss
Iambe-20b-DARE-v2-Q4_0.gguf	Q4_0	11.292 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Iambe-20b-DARE-v2-Q4_K_S.gguf	Q4_K_S	11.367 GB	small, greater quality loss
Iambe-20b-DARE-v2-Q4_K_M.gguf	Q4_K_M	12.042 GB	medium, balanced quality - recommended
Iambe-20b-DARE-v2-Q5_0.gguf	Q5_0	13.771 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Iambe-20b-DARE-v2-Q5_K_S.gguf	Q5_K_S	13.771 GB	large, low quality loss - recommended
Iambe-20b-DARE-v2-Q5_K_M.gguf	Q5_K_M	14.157 GB	large, very low quality loss - recommended
Iambe-20b-DARE-v2-Q6_K.gguf	Q6_K	16.404 GB	very large, extremely low quality loss
Iambe-20b-DARE-v2-Q8_0.gguf	Q8_0	21.247 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/Iambe-20b-DARE-v2-GGUF --include "Iambe-20b-DARE-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/Iambe-20b-DARE-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'