Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apple M5 chip

apple.com

Post reply on HN
Print view View original

1–10 of 1001 posts

Re: Apple M5 chip

#2

Post by nik736 »

This is only the base model, no upgrades yet for the Pro/Max version. The memory bandwidth is 153GB/s which is not enough to run viable open source LLM models properly.

Re: Apple M5 chip

#4

Post by airza »

I get they want to have a lot of their own swift-based bindings but I wish they could also keep their MPS pytorch bindings up to date...

Re: Apple M5 chip

#5

Post by simonw »

heystefan wrote: post #3

Is it me or did they use to avoid calling it "AI"?

Yeah, they rebranded it "Apple Intelligence" but this press release appears to be mostly using AI in the same (vague) way that the rest of the industry does.

Also just noticed this:

"And now with M5, the new 14-inch MacBook Pro and iPad Pro benefit from dramatically accelerated processing for AI-driven workflows, such as running diffusion models in apps like Draw Things, or running large language models locally using platforms like webAI."

First time I've ever heard of webAI - I wonder how they got themselves that mention?

Re: Apple M5 chip

#10

Post by quest88 »

nik736 wrote: post #2

This is only the base model, no upgrades yet for the Pro/Max version. The memory bandwidth is 153GB/s which is not enough to run viable open source LLM models properly.

What do you mean by properly? What’s the behavior one would observe if they did run an llm?
Post reply on HN