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

Apple introduces M6 and M5 Ultra

apple.com

Post reply on HN
Print view View original

771–780 of 1001 posts

Re: Apple introduces M6 and M5 Ultra

#771

Post by stmw »

greenowl wrote: post #581
alluro2 wrote: post #524

I was blown away by M1 Pro, and used it for 4 years before it became a little sluggish, and replacing it with an Asus S16 running on Ryzen AI 9 HX 370 (an excellent laptop). One of the main reasons was missing my old Linux setup. I've briefly tested M5 Pro in an Apple store and was surprised by how quick it felt and did anything. A tangible and significant difference, and I really feel it would be good getting it, or…

Still rocking an M1 Air - 2020 build. 8GB ram. No slowdown or deterioration at all. Battery health reports the battery max capacity at 84%. Best computer I've ever owned, by far.

Which MacOS version are you on, out of curiosity? Do others see the same software issues?

Re: Apple introduces M6 and M5 Ultra

#772

Post by Fuzzwah »

echelon wrote: post #766
plasticeagle wrote: post #605

Earlier quoted context omitted.

M1 Pro 2021 16GB RAM Feels as snappy and impressive as the first day I got it. I never need to close apps, or reboot. I record multitrack audio on it without any perceptible latency. I write code on it. It's the best computer I've ever owned by a significant margin.

MacBook is great hardware, but I really hate MacOS. It feels perpetually cellophane wrapped, and I don't like any of the window management. Finder is particularly awful too. You should be able to deeply tweak how window management works, but Mac won't let you do that. I'd run Linux on the hardware if it wasn't a hack.

Rectangle solved my macos window management annoyances.

https://rectangleapp.com/

Not involved in dev of this, just a happy user

Re: Apple introduces M6 and M5 Ultra

#773

Post by wmf »

Humphrey wrote: post #739
gardaani wrote: post #169

Rumors say that Apple will only release M6 base variant and skips M6 Pro, M6 Max and M6 Ultra variants to concentrate all efforts to create a good AI capable M7: "According to reports from Bloomberg, Apple will be skipping its M6 Pro, M6 Max, and M6 Ultra chips to accelerate development of the M7 chip. That means the only chip to be released from the M6 family will be the base M6. The reason for this break with tradi…

I wonder when/if we will start to see Apple include a silicon encoded model into their chips. Similar to Taalas build Llama 3.1 silicon with 17,000 tok/s inference. So could the M7 actually include an AFM 3B model, alongside a generic neural engine?

That model would be larger and more expensive than the entire M7 chip.

Re: Apple introduces M6 and M5 Ultra

#775

Post by rahkiin »

spudlyo wrote: post #742
cortesoft wrote: post #563

Earlier quoted context omitted.

What would you want Apple to do to improve the developer experience?

Improve the speed of APFS. Like try forking off a job to create a bunch of git worktrees in on APFS vs EXT4 -- it's significantly slower. Deleting a ton of files, cloning repos, hardlink performance, etc; APFS performance is poor compared to just about any other Linux filesystem.

The grass is always greener for some problem somewhere.

Try doing what you write on a (corporate) Windows machine with NTFS and file filters

Re: Apple introduces M6 and M5 Ultra

#776

Post by tyre »

Humphrey wrote: post #739
gardaani wrote: post #169

Rumors say that Apple will only release M6 base variant and skips M6 Pro, M6 Max and M6 Ultra variants to concentrate all efforts to create a good AI capable M7: "According to reports from Bloomberg, Apple will be skipping its M6 Pro, M6 Max, and M6 Ultra chips to accelerate development of the M7 chip. That means the only chip to be released from the M6 family will be the base M6. The reason for this break with tradi…

I wonder when/if we will start to see Apple include a silicon encoded model into their chips. Similar to Taalas build Llama 3.1 silicon with 17,000 tok/s inference. So could the M7 actually include an AFM 3B model, alongside a generic neural engine?

Why would a local model for a consumer device need 17k tok/s?

Apple is better off building chips with generalizable TPUs (or equivalent) so they can upgrade/patch models.

Re: Apple introduces M6 and M5 Ultra

#777

Post by dongliliu »

SilverSlash wrote: post #25

The 512GB Ultra is amazing, sure. But who is it for exactly? VC funded big spender founders? In that case why would they need local AI? The ultra rich enthusiast? But there can't be too many of those. So who actually buys these?

Aside from high-spending users, I think many people use it as a productivity tool. If you can use it to make money, and the money you earn far exceeds the monthly payment, why not make your work smoother?

Re: Apple introduces M6 and M5 Ultra

#778

Post by ActorNightly »

nomel wrote: post #587
ActorNightly wrote: post #453

Earlier quoted context omitted.

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…

That's 6 YEARS of their cloud inference! And, you have to include power. Where I am, the power for a rig with 2x 3090, running for four hours a day, would be around $70/month! It's kinda like datacenter only exist to optimize compute cost through oversubscription of hardware/time share, cheaper business energy rates, and bulk discounts, compared to self hosting. ;)

Running local models isn't about the cost, its about owning your own data and being able to run uncensored models. If you just want to code with an assistant, local inference is by far not worth it.

You also don't need to run the models 24/7, nor is your computer gonna be doing inference all the time when you are coding.

Re: Apple introduces M6 and M5 Ultra

#779

Post by tyre »

curious_cat_163 wrote: post #197
gardaani wrote: post #169

Rumors say that Apple will only release M6 base variant and skips M6 Pro, M6 Max and M6 Ultra variants to concentrate all efforts to create a good AI capable M7: "According to reports from Bloomberg, Apple will be skipping its M6 Pro, M6 Max, and M6 Ultra chips to accelerate development of the M7 chip. That means the only chip to be released from the M6 family will be the base M6. The reason for this break with tradi…

> I'd skip M5 and M6 chips for LLM work and wait for a year for M7. Please say more? Is it because it is a one-time cost, unlike a recurring subscription of Claude/Codex?

If you expect a large leap in performance, buying now means that (a) you will want to buy again in a year but (b) the large leap in performance hurts the resale of what you buy today.

Local models will be that much better in a year, so unless you have to have a top-of-the-line local rig today (the argument goes), stick with Claude for another year.

Re: Apple introduces M6 and M5 Ultra

#780

Post by barrell »

plasticeagle wrote: post #605
greenowl wrote: post #581

Earlier quoted context omitted.

Still rocking an M1 Air - 2020 build. 8GB ram. No slowdown or deterioration at all. Battery health reports the battery max capacity at 84%. Best computer I've ever owned, by far.

M1 Pro 2021 16GB RAM Feels as snappy and impressive as the first day I got it. I never need to close apps, or reboot. I record multitrack audio on it without any perceptible latency. I write code on it. It's the best computer I've ever owned by a significant margin.

M1 Pro 2021 16GB RAM as well.

However, I live with Activity Monitor open at all times. The computer constantly grinds to a halt, and I have to force quit apps at least 10 times per day.

Not really Apple's fault though, just most apps use around 4GB of RAM these days even when they're idle. Some use upwards of 16GB.

I've watched the computer slowly get obsoleted over time, not because the hardware is too old, but because software just get's worse every year.

Post reply on HN