They have 10x inference speed. Try Mistral and get awed. | Hacker News

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

		arisAlexis 3 months ago \| parent \| context \| favorite \| on: Cerebras systems raises $1.1B Series G They have 10x inference speed. Try Mistral and get awed.

aurareturn 3 months ago [–]

They're roughly 2.5x faster. https://www.cerebras.ai/press-release/maverick

Not 10x. But at greater cost and lower scale.

arisAlexis 3 months ago | [–]

Sources for greater cost and lower scale?

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