• lime!@feddit.nu
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    7 hours ago

    that’s old data. inference uses more than training now, since usage has gone up significantly. they traded places in march or april 2025.

    • Elvith Ma'for@feddit.org
      link
      fedilink
      English
      arrow-up
      2
      ·
      5 hours ago

      That’s the problem of reference. Your individual queries might not consume much - especially when compared to the training - but the more people use it, the more the whole consumption is. At some point running those models will consume more than training them