Re:Ferret: A Multimodal Large Language Model by Apple
by Someone on Saturday December 23, 2023 @03:04PM
(#38747638)
Running a LLM on-device alongside other apps (i.e. without it taking up all phone resources), and it being reasonably fast may well require more powerful hardware than they ever sold.
A voice assistant that takes 3 seconds to reply and then takes half a second per word is a nice demo, but not a product Apple wants to sell.
And yes, some people will say they rather have that than nothing on their hardware, but “the Internet” would say iOS 18 is slow, eats battery life, etc, damaging Apple’s brand.
A voice assistant that takes 3 seconds to reply and then takes half a second per word is a nice demo, but not a product Apple wants to sell.
And yes, some people will say they rather have that than nothing on their hardware, but “the Internet” would say iOS 18 is slow, eats battery life, etc, damaging Apple’s brand.