GGUF Variants

#2
by DakkaWolf - opened

Hi! Me again!

I made available the entire list of modern actively used Llama.cpp quantizations (all I variants, all K variants, Q8_0 and BF16) with the appropriate importance matrix and KL Divergence metrics.

You can find it here :)

Heyo! Left a LENGTHY reply on the other thread, but THANK YOU AGAIN!
I have no experience making quants, so I appreciate someone taking the time to make proper quants of my models! c:

Sign up or log in to comment