News for hackers. Stuff that matters.
Re:The path to ubiquitous AI (17k tokens/sec) by cheema33 on Friday February 20, 2026 @09:09AM (#47088244)
Yes. You can allow multiple people to use a single chip. A slower solution will be able to service far fewer users.
Re:The path to ubiquitous AI (17k tokens/sec) by xnx on Friday February 20, 2026 @09:27AM (#47088447)
Right, but it is also possible it's cheaper to use 42 Google TPUs for a second than one of these.