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

Apple caught off guard by AI demand for Mac Mini and Mac Studio

macrumors.com

Post reply on HN
Print view View original

621–630 of 636 posts

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#621

Post by redox99 »

qeternity wrote: post #284
redox99 wrote: post #193

Earlier quoted context omitted.

32GB of fast unified memory is enough for Qwen 3.8 27B. - 16GB for the weights at Q4 - 9GB for the full 256K context at Q8 - 7GB spare for overhead and system. The problem is that these Macs have 32GB of slow unified memory. Edit: I'm thinking of a headless Mac mini, if you meant running it on the same machine you're using of course you'll need more memory, but LLMs are best served from a headless server so that's wh…

> Edit: I'm thinking of a headless Mac mini, if you meant running it on the same machine you're using of course you'll need more memory, but LLMs are best served from a headless server so that's what I'd recommend. What? LLMs are best served from a massive PD disaggregated cluster of B300s connected via NVLink. If you're running LLMs on a Mac Mini, it's because you want to run local, not because it's the best setup.

>massive PD disaggregated cluster of B300s connected via NVLink.

So a headless server.

Macs were mentioned because that's what the post is about. It could be a PC (I use a 2x3090 PC). The point is that it's a better experience to have a box dedicated to the LLM than running it in your system. Obviously in your home, so local.

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#622

Post by xnx »

nullbio wrote: post #352

I'm convinced that this is just guerilla marketing from Apple. When this started spreading a day or two ago, it was all from no-name spam media sites that are paid to publish articles. They all claimed "a source" is where they got the intel, without specifying the source. It was spreading like wildfire on socials. The same thing happened with Mac Mini's and OpenClaw. Nobody cared about or was using Mac Mini's for Ope…

Not exactly guerilla marketing, but decades of traditional marketing bearing fruit in people who fetish-ize Apple products, need to socially signal how cutting edge thy are, and have too much disposable income.

I follow a lot of people on Twitter who were one-upping each other about how much hardware they had bought (now gathering dust0 to run their Claw assistants. Those same people are now buying some toy robot duck?

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#623

Post by bensyverson »

nullbio wrote: post #613
bensyverson wrote: post #530

Earlier quoted context omitted.

This is exactly the kind of paranoid conspiracy thinking I was talking about. If you see red yarn between everything, you're impervious to reality. Honestly, I'm an Apple user since 1988 and shareholder. I use my full-ass name on hn. I wish they'd give me money to promote the brand, but in reality they have something even more valuable than paid shitposting: authentic word of mouth and devoted users. That comes out o…

I prefer the term "unwitting accomplice", others prefer the term "useful idiot".

Ah yes, have you read Seth Godin's "1000 unwitting accomplices?" In Marketing 101 classes, the first session is usually "Recruiting Useful Idiots."

You seem to have product marketing all figured out!

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#624

Post by LtWorf »

watt3rpig wrote: post #545
LtWorf wrote: post #430

Earlier quoted context omitted.

> They honestly don’t need to, because they’re making an avalanche of cash from the iPhone. That… isn't how capitalism works…

Tim apple already has a few million dollars, why would he want need any more?

He's in a competition with his friends on who gets the highest score.

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#625

Post by TechSquidTV »

Grombobulous wrote: post #398
TechSquidTV wrote: post #130

Earlier quoted context omitted.

In my limited experience, not quite yet but we are damn close. Qwen 3.8 27b is it. If I could run this as a decent speed, I would no longer need cloud models at all. I'm actually currently trying it out in the cloud to pay for the inference speed but the model is fully runnable at home. I realistically costs $5-10k to replicate a ChatGPT like agent. And it doesn't scale. That's still really close. And models and quan…

I could believe that especially with some of the chips playing catch-up. E.g., the M7 chip is rumored to be the one where Apple has poured really serious effort into local AI performance where previous generations seem to have mostly been coincidentally good at it. Maybe this is an incorrect opinion but I don’t personally think that the M1-M3 or maybe M4 or even M5 chips were designed with LLM inference in mind at al…

They were not. Apple refused to acknowledge what they had.

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#626

Post by caycep »

jldugger wrote: post #245
caycep wrote: post #122

Earlier quoted context omitted.

to their credit, there was a lot of work behind "luck". Jensen showed up in person in 2017 in NEURIPS and he and likely a lot of his top brass basically sat down and read the entire conference proceedings/abstracts; there was likely a lot of work behind the scenes to behind the ML research pivot.

And 2017 was _late_ in their pivot. They'd been active for much, much longer. Last winter break I sat down to watch every GTC keynote, going back to 2009[1]. Even then, he's talking about expanding to non-graphics workloads. Google's GPU paper[2] just slotted naturally into their existing narrative and were happy to support it. "fortune favors the prepared" as they say. [1]: https://www.youtube.com/watch?v=fYuH2Kl_b9…

They definitely were sponsoring ML conferences before 2017, but symbolically, having Jensen/the CEO actually show up at a dedicated session and demonstrate detailed technical knowledge of the conference proceedings in my mind was a turning point. Albeit I remember his words to the crowd of grad students and post docs at the time: "Only Nvidia would announce their flagship card...to an audience who is completely broke!!"

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#627

Post by andai »

bensyverson wrote: post #548
andai wrote: post #538

Earlier quoted context omitted.

>This is exactly the kind of paranoid conspiracy thinking I was talking about. This sounds exactly like the kind thing that someone running a psyop for Apple would say.

Flawless logic! I can’t believe I got busted again… The other lizard people are going to be so disappointed. I’m already on probation for leaking the fact that the Earth is flat and bungling the JFK thing. Now they’ll probably pull me off the microwave mind reading project too.

This is a beautiful example of a technique called poisoning the well.

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#628

Post by ActorNightly »

srslack wrote: post #370
nullbio wrote: post #352

I'm convinced that this is just guerilla marketing from Apple. When this started spreading a day or two ago, it was all from no-name spam media sites that are paid to publish articles. They all claimed "a source" is where they got the intel, without specifying the source. It was spreading like wildfire on socials. The same thing happened with Mac Mini's and OpenClaw. Nobody cared about or was using Mac Mini's for Ope…

I am using Mac studios for local inference, but not for openclaw. It was simply the best bang for the buck at the time, and the software side of things has gotten even better since then. I haven’t run the pricing comparison but I have a feeling with the direction they’re heading that it’s better to hold off for m6 as it may assuage various bottlenecks if you are latency sensitive.

>It was simply the best bang for the buck at the time,

I wouldn't have a problem with Apple fanboys if they just stated that they like Macs, but for some reason you have no problem with just straight up LYING. Or at least being so deluded that you state things that are so easy to prove false as fact.

I.e, 600 gb/sec is dogshit slow compared to vram speeds.

Re: Apple caught off guard by AI demand for Mac Mini and Mac Studio

#630

Post by adolph »

aurareturn wrote: post #591
adolph wrote: post #151

Earlier quoted context omitted.

> an organization that was primed to recognize and pounce on the next big thing e.g.: previous crypto hype-cycle https://www.pcgamer.com/nvidia-cmp-graphics-card-availabilit...

They didn't make their GPUs for crypto. Crypto companies just bought a lot of their GPUs. If they had a choice, they would have sold every GPU to gamers instead because a crypto boom was always followed by a crash which flooded the market with used GPUs and crashed Nvidia's stock price.

> They didn't make their GPUs for crypto.

Sure they did and still do. They did a good job of managing the bubble but participate in the market nontheless. Read the above article: Nvidia has promised that its new lineup of cryptocurrency mining GPUs, called CMP for short, won't impact the supply of GeForce graphics cards for PC gamers. . . Since these cards are destined for mining rigs they will also lack video outputs. That may mean the resale value is diminished, which has been one reason why miners prefer gaming graphics cards.

Or take it from the horse's mouth [0]:

  NVIDIA Cmp Hx
  Dedicated GPU for Professional Mining
0. https://www.nvidia.com/en-us/cmp/
Post reply on HN