• thingsiplay@lemmy.ml
    link
    fedilink
    English
    arrow-up
    3
    ·
    2 days ago

    I have 8gb VRAM and use local LLM for Ai. xD Thanks to Vulkan it partially runs on GPU and partially on CPU, so its not too slow running “bigger” models.

    And no, before anyone downvotes me, I am not an Ai bro. I do not generate everything with Ai (would be difficult with low end hardware anyway).

    • stylusmobilus@aussie.zone
      link
      fedilink
      English
      arrow-up
      2
      ·
      2 days ago

      Yeah it’s certainly not too small for professional applications that don’t require huge amounts of power. If it’s cheap enough at the time I might look at this for my next build.