tensorblock/nanollama-GGUF

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

imdatta0/nanollama - GGUF

This repo contains GGUF format model files for imdatta0/nanollama.

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
nanollama-Q2_K.gguf	Q2_K	0.027 GB	smallest, significant quality loss - not recommended for most purposes
nanollama-Q3_K_S.gguf	Q3_K_S	0.031 GB	very small, high quality loss
nanollama-Q3_K_M.gguf	Q3_K_M	0.033 GB	very small, high quality loss
nanollama-Q3_K_L.gguf	Q3_K_L	0.035 GB	small, substantial quality loss
nanollama-Q4_0.gguf	Q4_0	0.039 GB	legacy; small, very high quality loss - prefer using Q3_K_M
nanollama-Q4_K_S.gguf	Q4_K_S	0.039 GB	small, greater quality loss
nanollama-Q4_K_M.gguf	Q4_K_M	0.040 GB	medium, balanced quality - recommended
nanollama-Q5_0.gguf	Q5_0	0.046 GB	legacy; medium, balanced quality - prefer using Q4_K_M
nanollama-Q5_K_S.gguf	Q5_K_S	0.046 GB	large, low quality loss - recommended
nanollama-Q5_K_M.gguf	Q5_K_M	0.046 GB	large, very low quality loss - recommended
nanollama-Q6_K.gguf	Q6_K	0.053 GB	very large, extremely low quality loss
nanollama-Q8_0.gguf	Q8_0	0.069 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/nanollama-GGUF --include "nanollama-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/nanollama-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'