Apple introduces M4 chip • Hacker News Board

Re: Apple introduces M4 chip

#661

Post by floam » Tue, May 07, 2024, 9:39 PM UTC

aborsy wrote: post #646

rsp1984 wrote: post #457

Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…

What are the example of the edge devices made by Apple?

MacBook, iPhone, iPad?

Re: Apple introduces M4 chip

#662

Post by doctor_eval » Tue, May 07, 2024, 9:40 PM UTC

cyberpunk wrote: post #296

gavin_gee wrote: post #238

I'm still rocking an iPad 6th generation. It's a video consumption device only. A faster CPU doesn't enable any new use cases. The only reason is the consumer's desire to buy more.

New oled does look like quite a nice display though...

Yep I have an OLED TV but was watching a movie on my (M1) iPad Pro last night, and realised how grey the blacks were.

Once you see it, etc.

Re: Apple introduces M4 chip

#663

Post by KptMarchewa » Tue, May 07, 2024, 9:40 PM UTC

klabb3 wrote: post #620

andsoitis wrote: post #539

Earlier quoted context omitted.

> In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending data up to the cloud for processing). Their primary business goal is to sell hardware. Yes, they’ve diversified into services and being a shopping mall for all, but it is about selling lu…

> but it is about selling luxury hardware. Somewhat true but things are changing. While there are plenty of “luxury” Apple devices like Vision Pro or fully decked out MacBooks for web browsing we no longer live in a world where tech are just lifestyle gadgets. People spend hours a day on their phones, and often run their life and businesses through it. Even with the $1000+/2-3y price tag, it’s simply not that much gi…

[flagged]

Re: Apple introduces M4 chip

#664

Post by LtdJorge » Tue, May 07, 2024, 9:42 PM UTC

gigatexal wrote: post #657

Anyone know if the ram multiples of the M4 are better than the M3? Example: could a base model M4 sport more than 24GB of ram?

Not for the iPad (8/16 GB)

Re: Apple introduces M4 chip

#665

Post by doctor_eval » Tue, May 07, 2024, 9:43 PM UTC

jsaltzman20 wrote: post #511

[dead]

Great People Units. OK. Nice recruitment pitch.

Re: Apple introduces M4 chip

#666

Post by deergomoo » Tue, May 07, 2024, 9:43 PM UTC

littlestymaar wrote: post #566

EduardoBautista wrote: post #13

The 256gb and 512gb models have 8gb of ram. The 1tb and 2tb models have 16gb. Not a fan of tying ram to storage. https://www.apple.com/ipad-pro/specs/

> 8gb of ram. WTF? Why so little? That's insane to me, that's the amount of RAM you get with a mid-range android phone.

I'm not defending Apple's absurd stinginess with RAM (though I don't think it's much of an issue on an iPad given how gimped the OS is), but I've never understood why high-end Android phones have 12/16+ GB RAM.

What needs that amount on a phone? 8GB on a desktop is...well it's not great, but it's usable, and usable for a damn sight more multi-tasking than you would ever do on a smartphone. Is it just because you need to look better on the spec sheet, like the silly camera megapixel wars of the 2010s?

Re: Apple introduces M4 chip

#667

Post by dancemethis » Tue, May 07, 2024, 9:44 PM UTC

rsp1984 wrote: post #457

Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…

Apple is privacy last, if anything. Forgotten PRISM already?

Re: Apple introduces M4 chip

#668

Post by thih9 » Tue, May 07, 2024, 9:44 PM UTC

When this arrives in MacBooks, what would that mean in practice? Assuming base M4 config (not max, not ultra - those were already powerful in earlier iterations), what kind of LLM could I run on it locally?

Re: Apple introduces M4 chip

#669

Post by huhuhu111 » Tue, May 07, 2024, 9:44 PM UTC

marinhero wrote: post #318

I get frustrated seeing this go into the iPad and knowing that we can't get a shell, and run our own binaries there. Not even as a VM like [UserLAnd]( https://userland.tech ). I could effectively travel with one device less in my backpack but instead I have to carry two M chips, two displays, batteries, and so on... It's great to see this tech moving forward but it's frustrating to not see it translate into a more si…

[dead]

Re: Apple introduces M4 chip

#670

Post by talldayo » Tue, May 07, 2024, 9:46 PM UTC

thih9 wrote: post #668

When this arrives in MacBooks, what would that mean in practice? Assuming base M4 config (not max, not ultra - those were already powerful in earlier iterations), what kind of LLM could I run on it locally?

> what kind of LLM could I run on it locally?

Anything up to the memory configuration it is limited to. So for base model M4, that likely means you have 8gb of memory with 4-5 of it realistically usable.