• Breve@pawb.social
      link
      fedilink
      English
      arrow-up
      5
      ·
      1 day ago

      Oh yeah for sure, I’ve run Llama 3.2 on my RTX 4080 and it struggles but it’s not obnoxiously slow. I think they are betting more software will ship with integrated LLMs that run locally on users PCs instead of relying on cloud compute.