tensorblock/luxia-21.4b-alignment-v1.0-GGUF

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

saltlux/luxia-21.4b-alignment-v1.0 - GGUF

This repo contains GGUF format model files for saltlux/luxia-21.4b-alignment-v1.0.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

Model file specification

Filename	Quant type	File Size	Description
luxia-21.4b-alignment-v1.0-Q2_K.gguf	Q2_K	7.563 GB	smallest, significant quality loss - not recommended for most purposes
luxia-21.4b-alignment-v1.0-Q3_K_S.gguf	Q3_K_S	8.783 GB	very small, high quality loss
luxia-21.4b-alignment-v1.0-Q3_K_M.gguf	Q3_K_M	9.751 GB	very small, high quality loss
luxia-21.4b-alignment-v1.0-Q3_K_L.gguf	Q3_K_L	10.590 GB	small, substantial quality loss
luxia-21.4b-alignment-v1.0-Q4_0.gguf	Q4_0	11.363 GB	legacy; small, very high quality loss - prefer using Q3_K_M
luxia-21.4b-alignment-v1.0-Q4_K_S.gguf	Q4_K_S	11.436 GB	small, greater quality loss
luxia-21.4b-alignment-v1.0-Q4_K_M.gguf	Q4_K_M	12.030 GB	medium, balanced quality - recommended
luxia-21.4b-alignment-v1.0-Q5_0.gguf	Q5_0	13.790 GB	legacy; medium, balanced quality - prefer using Q4_K_M
luxia-21.4b-alignment-v1.0-Q5_K_S.gguf	Q5_K_S	13.790 GB	large, low quality loss - recommended
luxia-21.4b-alignment-v1.0-Q5_K_M.gguf	Q5_K_M	14.134 GB	large, very low quality loss - recommended
luxia-21.4b-alignment-v1.0-Q6_K.gguf	Q6_K	16.369 GB	very large, extremely low quality loss
luxia-21.4b-alignment-v1.0-Q8_0.gguf	Q8_0	21.201 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/luxia-21.4b-alignment-v1.0-GGUF --include "luxia-21.4b-alignment-v1.0-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/luxia-21.4b-alignment-v1.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'