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

Apple M3 Ultra

apple.com

Post reply on HN
Print view View original

741–750 of 1001 posts

Re: Apple M3 Ultra

#741

Post by lukevp »

hedora wrote: post #416
aurareturn wrote: post #365

Earlier quoted context omitted.

High TDP? You mean server-grade CPUs? Apple doesn't make those.

Indeed. The M3 Ultra is in the midrange where they duke it out. Similarly, for its niche, the iPhone CPU is was better than AMD’s low end processors. Anyway the Apple config in the article costs about 5x more than a comparable low end AMD server with 512GB of ram, but adds an NPU. AMD has NPUs in lower end stuff; not sure about this TDP range.

How is that comparable? On-package RAM is lower latency and higher bandwidth and also much more expensive than external DDR5 sticks.

Re: Apple M3 Ultra

#742

Post by a1o »

Matl wrote: post #610
staticman2 wrote: post #511

Earlier quoted context omitted.

Smaller, dumber models are faster than bigger, slower ones. What model do you find fast enough and smart enough?

Not OP but I am finding the Qwen 2.5 32b distilled with DeepSeek R1 model to be a good speed/smartness ratio on the M4 Pro Mac Mini.

How much RAM?

Re: Apple M3 Ultra

#744

Post by ksec »

DidYaWipe wrote: post #713
swivelmaster wrote: post #426

Earlier quoted context omitted.

You could always just open a few Chrome tabs…

[flagged]

>Edit: WTF, someone downvoted "Enjoy the upvotes?" Pathetic.

You should read HN posting Guidelines if you want to understand why. Although I guess mostly in this case it is someone fat thumbed downvote.

Re: Apple M3 Ultra

#745

Post by ksec »

swivelmaster wrote: post #426
cxie wrote: post #325

Earlier quoted context omitted.

Guess what? I'm on a mission to completely max out all 512GB of mem...maybe by running DeepSeek on it. Pure greed!

You could always just open a few Chrome tabs…

It may not be Firefox in terms of hundreds or thousands of tabs but Chrome has gotten a lot more memory efficient since around 2022.

Re: Apple M3 Ultra

#747

Post by jauntywundrkind »

ZeroTalent wrote: post #687
InTheArena wrote: post #55

Earlier quoted context omitted.

Every single AI shop on the planet is trying to figure out if there is enough compute or not to make this a reasonable AI path. If the answer is yes, that 10k is a absolute bargain.

No, because there is no CUDA. We have fast and cheap alternatives to NVIDIA, but they do not have CUDA. This is why NVIDIA has 90% margins on its hardware.

CUDA is simply not important for modern vLLM and many many others. DeepSeek V3 works great on SGLang. https://www.amd.com/en/developer/resources/technical-article...

Can you do absolutely everything? No. But most models will run or retrain fine now without CUDA. This premise keeps getting recycled from the past, even as that past has grown ever more distant.

Re: Apple M3 Ultra

#748

Post by KerrAvon »

cubefox wrote: post #339
gield wrote: post #198

Earlier quoted context omitted.

Face ID, taking pictures, Siri, ARKit, voice-to-text transcription, face recognition and OCR in photos, noise filtering, ...

These have been possible in much smaller smartphone chips for years.

Yes, they have.

> September 12, 2017; 7 years ago

https://en.wikipedia.org/wiki/Apple_A11#Neural_Engine

Re: Apple M3 Ultra

#749

Post by KerrAvon »

cubefox wrote: post #707
stouset wrote: post #484

Earlier quoted context omitted.

Possible != energy efficient, which is important for mobile devices.

If the energy efficiency of things like Face ID was indeed so far so bad that you need a more efficient M3 Ultra, how come Face ID was integrated into smartphones years ago, apparently without significant negative impact on battery life?

You seem to be arguing with a strawman here -- who said you need an M3 Ultra for energy efficient Face ID?

Re: Apple M3 Ultra

#750

Post by jauntywundrkind »

burnerthrow008 wrote: post #374
PaulHoule wrote: post #245

Earlier quoted context omitted.

That article says you can connect them through the Thunderbolt 5 somehow to form clusters.

I wonder if that’s something new, or just the same virtual network interface that’s been around since the TB1 days (a new network interface appears when you connect two Macs with a TB cable)

Its the same host-to-host usb network, I believe.

I'm super interested in the clustering capability. At launch people said they were only getting like 11Gbps from their TB4 drive arrays, which was really way less than expected.

Apple does kind of advertise that each TB port has its own controllers. Which gives me hope that whatever 1x port can do 6x can do 6x better.

AMD's Strix Halo victory feels much more shallow today. Eventually 48GB or 64GB sticks will probably expand Strix Halo to 192 then 256GB. But Strix Halo is super super io starved, is basically a desktop of IO, with no way to easily host-to-host, and Apple absolutely understands that the use of a chip is bounded by what it can connect to. 6x TB5, if even half true, will be utterly outstanding.

It's been so so so so cool to see Non-Transparent Bridging atop thunderbolt, so one host can act like a device. Since it's PCIe, that hypothetically would allow amazing RDMA over TB. USB4 mandates host to host networking, but I have no idea how it is implemented and I suspect it's no where near as close to the metal.

Post reply on HN