tensorblock/Yi-1.5-9B-32K-GGUF

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

01-ai/Yi-1.5-9B-32K - GGUF

This repo contains GGUF format model files for 01-ai/Yi-1.5-9B-32K.

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
Yi-1.5-9B-32K-Q2_K.gguf	Q2_K	3.124 GB	smallest, significant quality loss - not recommended for most purposes
Yi-1.5-9B-32K-Q3_K_S.gguf	Q3_K_S	3.631 GB	very small, high quality loss
Yi-1.5-9B-32K-Q3_K_M.gguf	Q3_K_M	4.027 GB	very small, high quality loss
Yi-1.5-9B-32K-Q3_K_L.gguf	Q3_K_L	4.369 GB	small, substantial quality loss
Yi-1.5-9B-32K-Q4_0.gguf	Q4_0	4.691 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Yi-1.5-9B-32K-Q4_K_S.gguf	Q4_K_S	4.724 GB	small, greater quality loss
Yi-1.5-9B-32K-Q4_K_M.gguf	Q4_K_M	4.963 GB	medium, balanced quality - recommended
Yi-1.5-9B-32K-Q5_0.gguf	Q5_0	5.688 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Yi-1.5-9B-32K-Q5_K_S.gguf	Q5_K_S	5.688 GB	large, low quality loss - recommended
Yi-1.5-9B-32K-Q5_K_M.gguf	Q5_K_M	5.828 GB	large, very low quality loss - recommended
Yi-1.5-9B-32K-Q6_K.gguf	Q6_K	6.748 GB	very large, extremely low quality loss
Yi-1.5-9B-32K-Q8_0.gguf	Q8_0	8.739 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/Yi-1.5-9B-32K-GGUF --include "Yi-1.5-9B-32K-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/Yi-1.5-9B-32K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'