▲ 240 ▼ What can an individual do to fight against tech billionaires? (lemmy.world) submitted 2 years ago by Live_Let_Live@lemmy.world to c/asklemmy@lemmy.world 94 comments fedilink hide all child comments
[–] MajorSauce@sh.itjust.works 2 points 2 years ago* (last edited 1 year ago) (2 children) Try hosting locally DeepSeek R1, for me the results are similar to ChatGPT without needing to send any into on the internet. LM Studio is a good start. permalink fedilink source parent hideshow 4 child comments replies: [–] dasenboy@lemm.ee 1 point 2 years ago Thanks I'm trying it now! permalink fedilink source parent [–] froh42@lemmy.world 1 point 2 years ago (2 children) Don't you need a fast GPU to do so? permalink fedilink source parent hideshow 4 child comments replies: [–] shadow@lemmy.sdf.org 2 points 2 years ago Any relatively new gaming PC from the last, what, 4? Years has enough power to run local LLMs. Maybe not the ginormous 70GB behemoth models, but the toned down ones are pretty damn good and if you don't mind waiting a few seconds while it thinks, you can run it completely locally as much as you want, and whenever you want. permalink fedilink source parent [–] MajorSauce@sh.itjust.works 1 point 2 years ago* You would benefit from it with some GPU offloading, this would considerably accelerate the speed of the answers. But you only need enough RAM to load the model at the bare minimum. permalink fedilink source parent
[–] froh42@lemmy.world 1 point 2 years ago (2 children) Don't you need a fast GPU to do so? permalink fedilink source parent hideshow 4 child comments replies: [–] shadow@lemmy.sdf.org 2 points 2 years ago Any relatively new gaming PC from the last, what, 4? Years has enough power to run local LLMs. Maybe not the ginormous 70GB behemoth models, but the toned down ones are pretty damn good and if you don't mind waiting a few seconds while it thinks, you can run it completely locally as much as you want, and whenever you want. permalink fedilink source parent [–] MajorSauce@sh.itjust.works 1 point 2 years ago* You would benefit from it with some GPU offloading, this would considerably accelerate the speed of the answers. But you only need enough RAM to load the model at the bare minimum. permalink fedilink source parent
[–] shadow@lemmy.sdf.org 2 points 2 years ago Any relatively new gaming PC from the last, what, 4? Years has enough power to run local LLMs. Maybe not the ginormous 70GB behemoth models, but the toned down ones are pretty damn good and if you don't mind waiting a few seconds while it thinks, you can run it completely locally as much as you want, and whenever you want. permalink fedilink source parent
[–] MajorSauce@sh.itjust.works 1 point 2 years ago* You would benefit from it with some GPU offloading, this would considerably accelerate the speed of the answers. But you only need enough RAM to load the model at the bare minimum. permalink fedilink source parent