• @PseudorandomNoise
    link
    English
    128 months ago

    Don’t you need specific CPUs for these AI features? If so, how is this going to work on the machines that don’t support it?

    • sacredbirdman
      link
      fedilink
      608 months ago

      Nope, they can use your NPU, GPU or CPU whatever you have… the performance will vary quite a bit though. Also, the larger the model the more memory it needs to run well.

    • @elliot_crane
      link
      English
      438 months ago

      With it being local it’s probably a small and limited model. I took a couple courses on machine learning years ago (before it got rebranded as “AI”), and you’d be surprised at how well a basic image recognition model can run on the lowest-spec macbook from 2012.

      • ferret
        link
        fedilink
        English
        298 months ago

        Tbh the inversion of typical intuition that is LLMs taking orders of magnitudes more memory than computer vision can mess people unfamiliar up on estimates of the hardware required

    • lemmyvore
      link
      fedilink
      English
      228 months ago

      You only need lots of precessing power to train the models. Using the models can be done on regular hardware.

    • @[email protected]
      link
      fedilink
      English
      78 months ago

      Running AI models isn’t that resource intensive. Training the models is the difficult part.

    • @KISSmyOSFeddit
      link
      English
      48 months ago

      The feature will obviously just be disabled on machines that don’t support it.