News for hackers. Stuff that matters.

A comment on How Taalas "prints" LLM onto a chip?. Parent comment

Re:How Taalas "prints" LLM onto a chip? by bigyabai on Sunday February 22, 2026 @06:59PM (#47116208)
> a lot of people will just drop their AI subscriptions.

For a 2.5 kW Server? I don't see it happening, your money and electricity is better spent on CUDA compute.

[ Parent | on HN ]
Re:How Taalas "prints" LLM onto a chip? by ivan_gammel on Monday February 23, 2026 @05:20AM (#47120370)
>For a 2.5 kW Server?

I don’t see any reason why this should not drop to 100-300W at peak with maybe 100W*h of daily usage on smartphones.

[ Parent | on HN ]