tensorblock/gpt-neoxt-20b-v13-GGUF

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

manojpreveen/gpt-neoxt-20b-v13 - GGUF

This repo contains GGUF format model files for manojpreveen/gpt-neoxt-20b-v13.

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
gpt-neoxt-20b-v13-Q2_K.gguf	Q2_K	7.755 GB	smallest, significant quality loss - not recommended for most purposes
gpt-neoxt-20b-v13-Q3_K_S.gguf	Q3_K_S	8.967 GB	very small, high quality loss
gpt-neoxt-20b-v13-Q3_K_M.gguf	Q3_K_M	10.770 GB	very small, high quality loss
gpt-neoxt-20b-v13-Q3_K_L.gguf	Q3_K_L	11.770 GB	small, substantial quality loss
gpt-neoxt-20b-v13-Q4_0.gguf	Q4_0	11.656 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gpt-neoxt-20b-v13-Q4_K_S.gguf	Q4_K_S	11.750 GB	small, greater quality loss
gpt-neoxt-20b-v13-Q4_K_M.gguf	Q4_K_M	13.135 GB	medium, balanced quality - recommended
gpt-neoxt-20b-v13-Q5_0.gguf	Q5_0	14.186 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gpt-neoxt-20b-v13-Q5_K_S.gguf	Q5_K_S	14.186 GB	large, low quality loss - recommended
gpt-neoxt-20b-v13-Q5_K_M.gguf	Q5_K_M	15.289 GB	large, very low quality loss - recommended
gpt-neoxt-20b-v13-Q6_K.gguf	Q6_K	16.874 GB	very large, extremely low quality loss
gpt-neoxt-20b-v13-Q8_0.gguf	Q8_0	21.851 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/gpt-neoxt-20b-v13-GGUF --include "gpt-neoxt-20b-v13-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/gpt-neoxt-20b-v13-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'