News for hackers. Stuff that matters.
Re:How Taalas "prints" LLM onto a chip? by mirekrusin on Sunday February 22, 2026 @03:24PM (#47114297)
gpt-oss is fp4 - they're saying they'll next try mid size one, I'm guessing gpt-oss-20b then large one, i'm guessing gpt-oss-120b as their hardware is fp4 friendly

There are no comments on this comment yet.