tensorblock/Poro-34B-GGUF

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

LumiOpen/Poro-34B - GGUF

This repo contains GGUF format model files for LumiOpen/Poro-34B.

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
Poro-34B-Q2_K.gguf	Q2_K	12.491 GB	smallest, significant quality loss - not recommended for most purposes
Poro-34B-Q3_K_S.gguf	Q3_K_S	14.415 GB	very small, high quality loss
Poro-34B-Q3_K_M.gguf	Q3_K_M	17.232 GB	very small, high quality loss
Poro-34B-Q3_K_L.gguf	Q3_K_L	18.776 GB	small, substantial quality loss
Poro-34B-Q4_0.gguf	Q4_0	18.647 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Poro-34B-Q4_K_S.gguf	Q4_K_S	18.790 GB	small, greater quality loss
Poro-34B-Q4_K_M.gguf	Q4_K_M	20.899 GB	medium, balanced quality - recommended
Poro-34B-Q5_0.gguf	Q5_0	22.630 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Poro-34B-Q5_K_S.gguf	Q5_K_S	22.630 GB	large, low quality loss - recommended
Poro-34B-Q5_K_M.gguf	Q5_K_M	24.320 GB	large, very low quality loss - recommended
Poro-34B-Q6_K.gguf	Q6_K	26.861 GB	very large, extremely low quality loss
Poro-34B-Q8_0.gguf	Q8_0	34.785 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/Poro-34B-GGUF --include "Poro-34B-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/Poro-34B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'