Make 8 bit quantized model version

#14
by nonetrix - opened

It would be nice if there was a 8 bit gguff version as well for less compressed model

This comment has been hidden
This comment has been hidden

It would be nice if there was a 8 bit gguff version as well for less compressed model

where you able to run it with llama.cpp?
can you share some code example?

Sign up or log in to comment