tensorblock/MM-ReMM-L2-20B-GGUF

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

Undi95/MM-ReMM-L2-20B - GGUF

This repo contains GGUF format model files for Undi95/MM-ReMM-L2-20B.

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
MM-ReMM-L2-20B-Q2_K.gguf	Q2_K	6.911 GB	smallest, significant quality loss - not recommended for most purposes
MM-ReMM-L2-20B-Q3_K_S.gguf	Q3_K_S	8.064 GB	very small, high quality loss
MM-ReMM-L2-20B-Q3_K_M.gguf	Q3_K_M	9.039 GB	very small, high quality loss
MM-ReMM-L2-20B-Q3_K_L.gguf	Q3_K_L	9.898 GB	small, substantial quality loss
MM-ReMM-L2-20B-Q4_0.gguf	Q4_0	10.517 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MM-ReMM-L2-20B-Q4_K_S.gguf	Q4_K_S	10.586 GB	small, greater quality loss
MM-ReMM-L2-20B-Q4_K_M.gguf	Q4_K_M	11.215 GB	medium, balanced quality - recommended
MM-ReMM-L2-20B-Q5_0.gguf	Q5_0	12.825 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MM-ReMM-L2-20B-Q5_K_S.gguf	Q5_K_S	12.825 GB	large, low quality loss - recommended
MM-ReMM-L2-20B-Q5_K_M.gguf	Q5_K_M	13.185 GB	large, very low quality loss - recommended
MM-ReMM-L2-20B-Q6_K.gguf	Q6_K	15.278 GB	very large, extremely low quality loss
MM-ReMM-L2-20B-Q8_0.gguf	Q8_0	19.787 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/MM-ReMM-L2-20B-GGUF --include "MM-ReMM-L2-20B-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/MM-ReMM-L2-20B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'