i got all the local LLM shit set up but idk man i'm like retarded with this shit, i get like 3-5 messages in and then it just gets stuck generating forever and nothing i've tried will mitigate that.

so yeah that's not gonna happen, i've already pushed it far back outside of my mind for now lol maybe i'll be able to do it with a better gpu or something a few years from now when tech is better anyway. i have a 2080ti but it is scuffed and i'm still running ddr4. i've heard turing isn't as good with generative AI stuff as later architectures are too.