News for hackers. Stuff that matters.
Re:Experimenting with Local LLMs on macOS by bigyabai on Monday September 08, 2025 @11:56AM (#45169883)
> $10 to 20k for a home LLM device isn't ridiculous.

At that point you are almost paying more than the datacenter does for inference hardware.

Re:Experimenting with Local LLMs on macOS by JumpCrisscross on Monday September 08, 2025 @12:05PM (#45169991)
> At that point you are almost paying more than the datacenter does for inference hardware

Of course. You and I don't have their economies of scale.

Re:Experimenting with Local LLMs on macOS by bigyabai on Monday September 08, 2025 @12:14PM (#45170108)
Then please excuse me for calling your one-man $10,000 inference device ridiculous.
Re:Experimenting with Local LLMs on macOS by JumpCrisscross on Monday September 08, 2025 @12:23PM (#45170228)
> please excuse me for calling your one-man $10,000 inference device ridiculous

It’s about the real price of early microcomputers.

Until the frontier stabilizes, this will be the cost of competitive local inference. Not pretending what we can run on a laptop will compete with a data centre.

Re:Experimenting with Local LLMs on macOS by simonw on Monday September 08, 2025 @12:38PM (#45170452)
Plenty of hobbies are significantly more expensive than that.
Re:Experimenting with Local LLMs on macOS by bigyabai on Monday September 08, 2025 @03:30PM (#45172800)
The rallying cry of money-wasters the world over. "At least it's not avgas!"
Re:Experimenting with Local LLMs on macOS by seanmcdirmid on Monday September 08, 2025 @03:54PM (#45173109)
Some people lose lots of money on boats, some people buy a fancy computer instead and lose less, although still a lot of, money.
Re:Experimenting with Local LLMs on macOS by rpdillon on Monday September 08, 2025 @03:16PM (#45172610)
I mean, not really? Yeah, I pay to go to the movies and sit in a theater that they let me buy a ticket for, but that doesn't mean people that want to set up a nice home theater are ridiculous, they just care more about controlling and customizing their experience.
Re:Experimenting with Local LLMs on macOS by grim_io on Tuesday September 09, 2025 @10:13AM (#45182226)
Some would argue that the home theater is a superior experience to a crowded, far away movie theater where the person's head in front of you takes up a quarter of the screen.

The same can't be said for local inference. It is always interior in experience and quality.

A reasonable home theater pays for itself over time if you watch a lot of movies. Plus you get to watch shows as well, which the limited theater program doesn't allow.

I can buy over 8 years of the Claude max $100 plan for the price of the 512GB M3 Ultra. And I can't imagine the M3 being great at this after 5 years of hardware advancement.

Re:Experimenting with Local LLMs on macOS by rpdillon on Sunday September 14, 2025 @10:30AM (#45240003)
> The same can't be said for local inference. It is always interior in experience and quality.

Not really. I do it because it offers me more control. That's higher quality in my book.

Re:Experimenting with Local LLMs on macOS by brookst on Tuesday September 09, 2025 @09:05AM (#45181408)
How is it not impressive to be able to do something at quantity 1 for roughly the same price megacorps get at quantity 100,000?

Try building a F1 car at home. I guarantee your unit cost will be several orders of magnitude higher than the companies who make several a year.

Re:Experimenting with Local LLMs on macOS by vonneumannstan on Monday September 08, 2025 @06:39PM (#45175033)
Almost? Isn't a single h100 like 30k which is the bare minimum to run a big model?