Ask HN: Can anyone run frontier AI models at usable speeds?

Hacker News Ask2026-11-07 00:540 views

Eight months ago, EXO labs promised fast inference on local hardware. But it is not fast enough. It takes a minute and a half to get a response through hermes, using Kimi K2.6. Is there hardware that a dev can buy that can actually offset cloud bills?

Comments URL: https://news.ycombinator.com/item?id=50394913

Points: 1

# Comments: 0

Source：https://news.ycombinator.com/item?id=50394913

My favorites

PreviousLooking for a CTO NextI tried to connect every GPU on the planet together (kinda)

The iPhone Duo has more than 100,000 optimized apps, Apple says

Apple's iPhone Duo has been officially on sale for two weeks, and the company said today that the App Store now has over

0The Verge

Product JSON-LD for WooCommerce: the fields AI shopping answers can actually use

If you want a WooCommerce product to show up in AI shopping answers, the Product structured data on the page is one of t

0dev.to

It's a weird time to buy a laptop, but the new MacBook Pro doesn't skimp on quality

Apple's new MacBook Pro is expensive as hell. Let's get that out there right away, because for a lot of people, it will

0Ars Technica

Could potential AI clones of GTA VI force a quicker official port?

Yesterday, when reporting on emerging efforts to pipe the console version of GTA VI through a PC's DLSS-powered Nvidia G

0Ars Technica

AI is the new dating dealbreaker

When Irene moved to San Francisco last year, she started using dating apps as a way to meet new people, get to know her