tensorblock/Tifa-Deepsex-14b-CoT-GGUF

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

ValueFX9507/Tifa-Deepsex-14b-CoT - GGUF

This repo contains GGUF format model files for ValueFX9507/Tifa-Deepsex-14b-CoT.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.

Filename	Quant type	File Size	Description
Tifa-Deepsex-14b-CoT-Q2_K.gguf	Q2_K	5.770 GB	smallest, significant quality loss - not recommended for most purposes
Tifa-Deepsex-14b-CoT-Q3_K_S.gguf	Q3_K_S	6.660 GB	very small, high quality loss
Tifa-Deepsex-14b-CoT-Q3_K_M.gguf	Q3_K_M	7.339 GB	very small, high quality loss
Tifa-Deepsex-14b-CoT-Q3_K_L.gguf	Q3_K_L	7.925 GB	small, substantial quality loss
Tifa-Deepsex-14b-CoT-Q4_0.gguf	Q4_0	8.518 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Tifa-Deepsex-14b-CoT-Q4_K_S.gguf	Q4_K_S	8.573 GB	small, greater quality loss
Tifa-Deepsex-14b-CoT-Q4_K_M.gguf	Q4_K_M	8.988 GB	medium, balanced quality - recommended
Tifa-Deepsex-14b-CoT-Q5_0.gguf	Q5_0	10.267 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Tifa-Deepsex-14b-CoT-Q5_K_S.gguf	Q5_K_S	10.267 GB	large, low quality loss - recommended
Tifa-Deepsex-14b-CoT-Q5_K_M.gguf	Q5_K_M	10.509 GB	large, very low quality loss - recommended
Tifa-Deepsex-14b-CoT-Q6_K.gguf	Q6_K	12.125 GB	very large, extremely low quality loss
Tifa-Deepsex-14b-CoT-Q8_0.gguf	Q8_0	15.702 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/Tifa-Deepsex-14b-CoT-GGUF --include "Tifa-Deepsex-14b-CoT-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/Tifa-Deepsex-14b-CoT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'