>>106273510
>>106275585
full sapport and full kvality saar

>>105746664
>There shouldn't be any difference because Q8 GGUF is 8 bit floating point, just different format.
another retarded take from debo

>>105744098
>switching between gguf and fp8
what gguf though? only Q8 is better than fp8

>>105731041
>what would be the best way to run it with minimal (preferably no) quality loss?
Q8 is really close to bf16 and it's only eating ~15gb of memory during inference

>>105635932
>Because Q8 is negligible quality difference to the full weights while allowing me to generate 8 images at a time easily, speeding up the generation by granting a free 1 image for each 8 time wise
what? Q8 and bf16 have the same speed though?

>>105605495
>>105605498
why are retards always so confident of themselves?