Most of those people will be dissapointed when they experience Q4 variants of those models getting stuck in loops.
I would wait till the ram crisis is over to fetch a future 64gb ram gpu to run Q8 models. Cloud inference until than.
Most of those people will be dissapointed when they experience Q4 variants of those models getting stuck in loops.
I would wait till the ram crisis is over to fetch a future 64gb ram gpu to run Q8 models. Cloud inference until than.
I'm excited to hear the ram crisis will be over. But will it?
Switching from Q4 to Q8 was a game changer when I upgraded