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
[ Parent
| on HN ]
There are no comments on this comment yet.