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

Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

bloomberg.com

Post reply on HN
Print view View original

171–180 of 396 posts

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#171

Post by lumost »

overfeed wrote: post #114
MisterKent wrote: post #57

Apple is actually interesting. They are one of the few companies with a chip / PC play with real power AND basically no play I'm the hyperscalar market. That means they're actually incentivized at least short term, to benefit PCs becoming strong enough to do local LLMs. Which makes this play make even more sense. Though, I've been saying for a while that the local AI inflectiom point is the death knell for these fron…

> Though, I've been saying for a while that the local AI inflectiom point is the death knell for these frontier labs. "Death knell" is a touch hyperbolic. Hardware that can only run quantized models that take up GBs in VRAM falls short of even an A100 (by almost an order of magnitude[0]), which in turn falls short of what an 8xH100 cluster can do (also by another order of magnitude[0]). I'm an avid believer in local…

The big question for local LLMs is whether there is a 100 tok/s model which requires less than 16 GB of memory and is competitive on most tasks with the cloud models.

There is some signal that this is possible through both hardware innovation and training/data improvements.

Cloud models have their own constraints - I can’t have opus4.8 spend 4 hours on a deep research question I had in the shower without spending money. I can’t do real time video game upscaling and graphics work in the cloud period.

A laptop is about an order of magnitude cheaper than a cloud server thanks to economies of scale, uptime requirements, and other factors.

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#172

Post by faeyanpiraat »

jimbokun wrote: post #112
ErneX wrote: post #9

Earlier quoted context omitted.

Problem is affording the ram…

Apple is finally going to realize Jobs vision where sand comes into the factory, is turned into RAM and CPU chips, then installed in a Mac or iPhone then shipped to a customer.

Isnt the proper kind of sand in short supply aswell?

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#173

Post by ttoinou »

vessenes wrote: post #7

The article says base M7 memory bandwidth is targeted at 240GB/s. M1 had 70 GB/s, M1 Pro: 200, M1 Max 400, M1 Ultra 800. Modern RTX 6000: ~1,600 or so. If we get a 1,200-1,500 GB/s bandwidth M7 variant in late 2027 with 512GB of RAM, that will be a very interesting chip. Tracking LLM size and performance improvements, I can imagine that being a sort of inflection point for local inference. I wonder what the power bud…

192gb or 256gb of RAM would be enough ! We could run real time large MoE models, REAPed for our usage (e.g. english agentic coding), dynamic quant 2-4bits

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#174

Post by 9dev »

Abishek_Muthian wrote: post #93
matheusmoreira wrote: post #83

Earlier quoted context omitted.

Indeed. If Apple makes it feasible to run models like GLM 5.2 at home, I will become their customer.

It's plausible but is the Apple Tax for a 1TB memory machine on top of current memory prices really worth it? I paid around $4000 for 4090m laptop with 16GB VRAM back in 2023, it's great but DoA for even quantized LLMs. I can run SLMs and fine tune it but that's it. We need one of those specialized inference chip startups to succeed and a PC manufacturer willing to bet on them against Nvidia for the local AI to find…

> I paid around $4000 for 4090m laptop

That's how much many developers currently spend on tokens - every day. Whatever "Apple Tax" applies to a device that can run a capable model offline will amortise itself in a blink.

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#175

Post by nicoty »

rhdjcnfj373 wrote: post #152
rjrjrjrj wrote: post #111

Earlier quoted context omitted.

I wasn't thinking of Asahi. Just pointing out that you can run all the standard unix/open source tools and apps on Mac OS (vi, git, qgis, blender, vsc, python, node, etc). With the advantage of higher quality hardware and generally less fiddling. But if you don't like it, switch. I don't see vendor lock-in.

A lot of convenient things come with the lock-in if you have >1 device Notes sync, Copy/Paste would be hard to give up and took zero effort

I don't now how the MacOS equivalent compares, but Linux/Windows has KDE Connect that I use for that https://kdeconnect.kde.org/

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#176

Post by marci »

drnick1 wrote: post #143
kennywinker wrote: post #127

Earlier quoted context omitted.

Doesn’t need to be a winner head to head. If it can do 90% of the tasks the big boys do, at 50% speed, for virtually no extra overhead cost save for the power consumed by a prompt - that’s gonna work for a lot of people. And that’s also basically where we’re at today. Qwen3.6 35b running quantized on 10 year old hardware solves basically all of my uses cases for agents except for coding. The frontier models are faste…

Consider this. One of the smallest Qwen models (4B parameters) powers my home automation voice assistant, and runs on CPU alone at >20 tok/s. It is enough for that use case, and could be made even better/faster with a modest GPU. It isn't as smart as some cloud-connected thingamajig, but I would never allow a literal Google or Amazon bug in my home. Huge SOTA models aren't relevant everywhere. Most people use LLMs fo…

But with Apple's AFM 3 architecture, we might end up with huge SOTA adjacent on devices with limited RAM.

They use a technique where you only load between 1B and 4B of a 20B dense model for an entire prompt run, not token by token like a MoE, and use mostly the low power ANE instead of GPU cores.

Now, imagine if/when they scale up to 100B or more? On a chip using 2W?

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#177

Post by Abishek_Muthian »

ramesh31 wrote: post #162
lowkeyokay wrote: post #106

Earlier quoted context omitted.

I recently bought a Mac mini M4 16 GB - mostly to run Immich. I assumed I needed a Linux box. After a lot of researched I was quite surprised that the mac was the cheapest option. So not always an Apple tax.

>" After a lot of researched I was quite surprised that the mac was the cheapest option. So not always an Apple tax." Apple has always been the most cost effective choice for the value you get going all the way back to the Apple II, it's just that the floor of that cost has always been high. Anyone who thinks otherwise is a just a fanboy one way or the other.

That's true only for the entry level macs. My M4 Mac Mini has the best Performance/value. But my workstation laptop with 32 cores, 96GB DDR5, Nvidia GPU costs lesser than Macs with lesser performance; not to mention I upgraded the RAM post purchase.

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#178

Post by SanjayMehta »

kennywinker wrote: post #127
overfeed wrote: post #114

Earlier quoted context omitted.

> Though, I've been saying for a while that the local AI inflectiom point is the death knell for these frontier labs. "Death knell" is a touch hyperbolic. Hardware that can only run quantized models that take up GBs in VRAM falls short of even an A100 (by almost an order of magnitude[0]), which in turn falls short of what an 8xH100 cluster can do (also by another order of magnitude[0]). I'm an avid believer in local…

Doesn’t need to be a winner head to head. If it can do 90% of the tasks the big boys do, at 50% speed, for virtually no extra overhead cost save for the power consumed by a prompt - that’s gonna work for a lot of people. And that’s also basically where we’re at today. Qwen3.6 35b running quantized on 10 year old hardware solves basically all of my uses cases for agents except for coding. The frontier models are faste…

This is what makes sense for me as well. All I need a local model is for playing with simple graphics: no gradients, at most ten colours which I can push through VTracer to get an SVG. Draw Things does the job, usually in 120 seconds or less.

Sometimes, I need a quick throwaway bit of python. That can take 30 minutes of my time.

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#179

Post by jurgenburgen »

aurareturn wrote: post #17
vessenes wrote: post #7

The article says base M7 memory bandwidth is targeted at 240GB/s. M1 had 70 GB/s, M1 Pro: 200, M1 Max 400, M1 Ultra 800. Modern RTX 6000: ~1,600 or so. If we get a 1,200-1,500 GB/s bandwidth M7 variant in late 2027 with 512GB of RAM, that will be a very interesting chip. Tracking LLM size and performance improvements, I can imagine that being a sort of inflection point for local inference. I wonder what the power bud…

A hypothetical M7 Ultra with LPDDR6 14.4Gbps memory would be 1.85 Tb/s. You're look at about 100 tokens/s for a 1T MoE 37B active 4bit model. It'd probably cost $30k or more I'm guessing if memory prices do not come down. Even at $30k, it could still be a relative bargain since an RTX Pro 6000 Blackwell 96GB card costs $12k today. The M3 Ultra with 512GB was around $8k before Apple discontinued it. I expect an M7 Ult…

> A hypothetical M7 Ultra with LPDDR6

That’s indeed very hypothetical considering that Apple silicon uses on-package HBM.

Re: Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

#180

Post by rjzzleep »

overfeed wrote: post #114
MisterKent wrote: post #57

Apple is actually interesting. They are one of the few companies with a chip / PC play with real power AND basically no play I'm the hyperscalar market. That means they're actually incentivized at least short term, to benefit PCs becoming strong enough to do local LLMs. Which makes this play make even more sense. Though, I've been saying for a while that the local AI inflectiom point is the death knell for these fron…

> Though, I've been saying for a while that the local AI inflectiom point is the death knell for these frontier labs. "Death knell" is a touch hyperbolic. Hardware that can only run quantized models that take up GBs in VRAM falls short of even an A100 (by almost an order of magnitude[0]), which in turn falls short of what an 8xH100 cluster can do (also by another order of magnitude[0]). I'm an avid believer in local…

Is it hyperbolic though? One of the best things about the compute and memory shortage is that people are going to insane lengths to optimize things to run on lower memory / lower compute devices. If we keep this up for a while and then ramp up memory and local compute production, that AI inflection point may actually come.

Of course, these are a lot of ifs.

Post reply on HN