Wow - actually pretty astonishing how fast their inference is. So fast it feels ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		bikelang 27 days ago \| parent \| context \| favorite \| on: Accelerating Gemma 4: faster inference with multi-... Wow - actually pretty astonishing how fast their inference is. So fast it feels fake?

qingcharles 27 days ago [–]

Yeah, when you find fast inference like that it almost feels like the answer arrives before you hit return. Now imagine it running locally with no server round-trip.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact