tensorblock/PiVoT-MoE-GGUF

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

maywell/PiVoT-MoE - GGUF

This repo contains GGUF format model files for maywell/PiVoT-MoE.

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

{system_prompt}{system_prompt}### Instruction: {prompt}### Response:

Filename	Quant type	File Size	Description
PiVoT-MoE-Q2_K.gguf	Q2_K	13.189 GB	smallest, significant quality loss - not recommended for most purposes
PiVoT-MoE-Q3_K_S.gguf	Q3_K_S	15.568 GB	very small, high quality loss
PiVoT-MoE-Q3_K_M.gguf	Q3_K_M	17.288 GB	very small, high quality loss
PiVoT-MoE-Q3_K_L.gguf	Q3_K_L	18.734 GB	small, substantial quality loss
PiVoT-MoE-Q4_0.gguf	Q4_0	20.345 GB	legacy; small, very high quality loss - prefer using Q3_K_M
PiVoT-MoE-Q4_K_S.gguf	Q4_K_S	20.523 GB	small, greater quality loss
PiVoT-MoE-Q4_K_M.gguf	Q4_K_M	21.824 GB	medium, balanced quality - recommended
PiVoT-MoE-Q5_0.gguf	Q5_0	24.840 GB	legacy; medium, balanced quality - prefer using Q4_K_M
PiVoT-MoE-Q5_K_S.gguf	Q5_K_S	24.840 GB	large, low quality loss - recommended
PiVoT-MoE-Q5_K_M.gguf	Q5_K_M	25.603 GB	large, very low quality loss - recommended
PiVoT-MoE-Q6_K.gguf	Q6_K	29.617 GB	very large, extremely low quality loss
PiVoT-MoE-Q8_0.gguf	Q8_0	38.360 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/PiVoT-MoE-GGUF --include "PiVoT-MoE-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/PiVoT-MoE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'