Now if only I can natively run Linux on their hardware.
Apple introduces M6 and M5 Ultra
471–480 of 1001 posts
Re: Apple introduces M6 and M5 Ultra
#472Earlier quoted context omitted.
Considering hard drives were $10k / GB in the Mac SE/30 days, that feels like a bargain too.
Sure, yes, compared to the prices of storage 35 years ago, it's a bargain. Compared to the prices of storage today, when people are presumably buying the product, it's actually a bad price.
Sure, but this thread started with somebody pointing out that these computer prices are in line with Mac SE/30 prices. I'm just carrying that over to cover storage and it's even more amazing how much we get for so little money.
Re: Apple introduces M6 and M5 Ultra
#473Re: Apple introduces M6 and M5 Ultra
#474Even w/the pricing spike, inflation adjusted we are back to roughly the prices of a new Mac SE/30 for something that can beat a turing test w/o sweating. I yield the floor to no one when it comes to pessimism, but that's incredible.
Yo... the Se/30 was worth it. dual floppies was so lame
Re: Apple introduces M6 and M5 Ultra
#475I run a lot of local models (I am always experimenting) on my 32G M2-Pro MacMini - I would love to upgrade. The financial aspects don’t work however: I can learn and experiment with what I have for local models, and I pay as I go on FireWorks.ai for open model inferencing and no matter how much I use this service my monthly bill is between $10 and $40 and much faster than any reasonable home rig. Hybrid ‘small local’…
Honest question - why are you so stuck on Macs for local inference? A 4 GPU linux box with 3090s, which are $1500 a piece right now, will blow this thing out of the water. Even 2x3090 rig will run most of the good local models like Gemma4:31b at 100+ tok/sec The VRAM of the GPUs are MUCH faster than the unified ram within Apple Silicon. The only difference is the initial model load, which takes longer from disk to VR…
Upgrading RAM is still probably cheaper than spending $6000 on a linux box. You're correct that inference will be much faster on the Linux box. But, the mac's unified memory can load larger models. And as OP mentions, it's still hard to beat cloud pricing at home.
Re: Apple introduces M6 and M5 Ultra
#476>fluid frame rates in demanding games like Mixtape. not getting on that bandwagon but wasn't that not the most demanding game as its a just a nonstop cutscene.
cutscenes are often the most demanding part of a game!
Re: Apple introduces M6 and M5 Ultra
#477I know, this is a bit of a meaningless comment, but it's funny in a way. Feels like late 90s again: - Xiaomi: We have matched Apple in CPU performance. - Apple: *Meep Meep...*
Reading Infinite Games, they tell an anecdote about a Microsoft exec on a flight telling an Apple exec that the Zune was a way better portable music player than the iPod. The Apple exec was just “yup, you’re probably right” and then soon after the iPhone dropped
That just sounds like a standard introvert response when one doesn’t want to walk.
Re: Apple introduces M6 and M5 Ultra
#478"M6 features a powerful, larger 12-core GPU that provides higher geometry rates and updated Dynamic Caching to deliver stunning visuals and fluid frame rates in demanding games like Mixtape." Why choose the worst game of the year? Just because it's made by the daughter of Larry Ellison?
I've never heard of Mixtape, but I'm surprised to see such a weirdly contemptuous post about a video game get so much traction on HN. At a glance, critical review aggregators are showing 80+ on this game. Is there some drama or culture war issue here that I'm missing?
Yes, it's a culture war thing and the commenters here are participating in it: https://www.pcgamer.com/games/adventure/mixtape-is-at-the-ce...
Re: Apple introduces M6 and M5 Ultra
#479Earlier quoted context omitted.
Local AI is the future, and a lot of people want the first mover advantage or to toy around with it. I know a guy with a small rack of Nvidia Spark machines that he uses for that purpose; it's as much as a decent used car.
But is it? If it’s cheap enough latency doesn’t matter. Unlike say cloud gaming, where latency does matter. I’ll take my games local and my text bots cloud
Of course. People are valuing privacy now, and it's almost inevitable that humans will seek to have more agency over a social contact, even if it's an artificial one.
Re: Apple introduces M6 and M5 Ultra
#480Earlier quoted context omitted.
In the ‘90s it was the opposite. - Apple: We have matched Intel in CPU performance thanks to this new PowerPC! ( Shows ad that uses carefully handpicked benchmarks to suggest that the PowerPC is actually faster when it really isn’t on average ) - Intel: Oh, we just found a 30% clock rate increase in the pocket of our other fab pants. - AMD: Hold my beer, I have the DEC Alpha guys making an x86 CPU… How about 64-bit w…
I had a G4 MacBook when I switched to the first-gen Intel MacBooks, and subjectively, the G4 performed much, much better. Probably because the best pairing for any Intel CPU is thermal throttling.
A lot of the important applications took a while to get ported. Also the last two generations of G4 hardware just overclocked basically unchanged chips. The 12" G4 laptop was infamous for slowly cooking your junk with their titanium shell.