You can run stuff on a little GPU, IGPU, or even just a CPU. You’ll be limited by RAM/VRAM, and obviously it’ll be slower, but it’ll work.
Comment on Where to start with setting up my own server?
breadsmasher@lemmy.world 6 days ago
random resource - of options. look up *ARR stacks
github.com/Rick45/quick-arr-Stack
LLMs
dont bother unless youre shelling out for a big ol gpu etc
frongt@lemmy.zip 6 days ago
wreckedcarzz@lemmy.world 5 days ago I have a server that I wanted to do this with, and cpu-only interference was several minutes for pretty simple tasks (all text, couple of sentences). I shelled out the cash for a 5060 Ti 16GB earlier this summer, and even with a pcie 3 x16 slot running at x4, I’m down to 5-30 second responses and rapid output speeds, even with large conversations. But the initial prompt/loading is still a couple of minutes by itself, so I leave the model in vram always.
BartyDeCanter@piefed.social 5 days ago
Or you can go straight to the source and use the Trash Guides