Cerebras achieves 2,500T/s on Llama 4 Maverick (400B)

Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by diggan on Saturday May 31, 2025 @06:56AM (#44143410)

> That’s prohibitively expensive

Assuming you experience is working within enterprise, you're then saying that cost is the biggest bottleneck currently?

Also surprising to me that enterprises would use out-of-the-box models like that, I was expecting at least fine-tuned models be used most of the time, for very specific tasks/contexts, but maybe that's way optimistic.

[ Parent | on HN ]

Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by threeseed on Saturday May 31, 2025 @07:08AM (#44143462)

Cost is irrelevant when compared to the salaries of the people using them so they will do basic cost controls but nothing too onerous. And cost is never a reason to prevent solutions being built and deployed.

And most enterprises aren't even doing anything advanced with AI. Just doing POCs with chat bots (again) which will likely fail (again). Or trying to do enterprise search engines which are pointless because most content is isolated per team. Or a few OCR projects which is pretty boring and underwhelming.

[ Parent | on HN ]

Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by baq on Saturday May 31, 2025 @05:23PM (#44147003)

Cost would be the biggest factor if price per token was the same but tokens were arriving 100x faster. (Not particularly unexpected I’d say.)

[ Parent | on HN ]