> single RTX 3080 20G, I got 10 tok/s initially
Add $200, buy a used 3060 and you won't need to offload cache to RAM. Yo'd have like 50-60 t/s with MTP enabled.
Add $200, buy a used 3060 and you won't need to offload cache to RAM. Yo'd have like 50-60 t/s with MTP enabled.
Maybe it's time for me to get a 3060 back again. :P