Given its extremely high energy and water consumption, the increased minimum system requirements driving premature hardware obsolescence, among other very problematic social and political issues, genAI/LLMs are not compatible with the values and goals of KDE Eco.

KDE is a diverse community and the opinions and projects of some KDE contributors are not representative of the entire community or KDE Eco projects.

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 1 month ago (1 child)

10-second responses you can fit 360 replies per hour, for a total of 1.8kWh per hour, ideally.

I find it kinda hard to believe that a prompt takes up an entire server for a full 10 seconds. That does not seem in any way scalable.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 1 month ago

    context-switching is expensive, but you are right that 10 seconds may be too long. i just pulled something.

    then again they've optimised the size of the machines to the point that a single rack can fit more than 100 blade servers, and a dc can have a thousand racks.

  • source
  • parent