Modelpublic

sthaps/self_cognition_Alice

sourceHugging Faceupdated 9mo agoView on Hugging Face

0likes103downloads

Model Card

selfcognitionAlice - GGUF

This repository contains GGUF weights for charent/self_cognition_Alice.

For a convenient overview and download list, visit our model page.

If you are unsure how to use GGUF files, refer to the llama.cpp documentation for more details.

bash

./llama-cli -m self_cognition_Alice-q4_k_m.gguf -p "Hello!"

(sorted by size, not necessarily quality)

Link	Type	Size/GB	Notes
GGUF	q2_k	0.28	very low quality, for testing
GGUF	q3km	0.32
GGUF	q4_0	0.36
GGUF	q4km	0.37	recommended, good balance
GGUF	q5km	0.41
GGUF	q8_0	0.60	near-full precision

Special thanks to the llama.cpp team for their amazing work.