Sjmarf@sh.itjust.works to Lemmy Shitpost@lemmy.world · 11 hours agoHow to clean a rescued pigeonsh.itjust.worksimagemessage-square105fedilinkarrow-up1914arrow-down19
arrow-up1905arrow-down1imageHow to clean a rescued pigeonsh.itjust.worksSjmarf@sh.itjust.works to Lemmy Shitpost@lemmy.world · 11 hours agomessage-square105fedilink
minus-squareHnerylinkfedilinkarrow-up1·2 hours agollama3 is not bad and you can easily run the smaller ones on an average desktop cornfuser
minus-squarePolarisFx@lemmy.dbzer0.comlinkfedilinkarrow-up1·2 hours agoBut slowly, I filled my home server with whatever CUDA capable cards I have and it’s fine for SD, but I found llama way too slow. I rented a dual A2000 instance for a couple weeks and it was bearable, but still not great.
llama3 is not bad and you can easily run the smaller ones on an average desktop cornfuser
But slowly, I filled my home server with whatever CUDA capable cards I have and it’s fine for SD, but I found llama way too slow. I rented a dual A2000 instance for a couple weeks and it was bearable, but still not great.