News for hackers. Stuff that matters.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by overfeed on Friday June 26, 2026 @12:30AM (#48682328)
> 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 LLMs, but I cannot deceive myself - data center accelerators will win on power dissipation numbers alone[1], even when giving generous allowances for higher efficiency on Apple chips - and assuming the Apple-efficiency advantage persists on the same TSMC process node.

0. Based on my unscientific fine-tuning training experiments across local and rented GPUs. YMMV for inference.

1. Unless Apple surprises everyone and brings back the XServe with M7, if not, then laptop and desktop for factors simply can't dump heat fast enough to compete head-to-head, and will be designed for lower input wattage.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by kennywinker on Friday June 26, 2026 @12:44AM (#48682413)
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 faster, and better at coding, but not so much that i’ll pay $200/month for them.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by drnick1 on Friday June 26, 2026 @01:17AM (#48682589)
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 for rather trivial tasks such as finding typos or drafting text.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by marci on Friday June 26, 2026 @02:54AM (#48683229)
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-focuse... by kinnth on Friday June 26, 2026 @04:02AM (#48683728)
I think we're also ignoring a potential innovative move in how models work.

If someone could splinter or fragment the models into more specific tasks i.e "spellchecker AI" and get these working as well as Sonnet 4.6-4.8 on those tasks on a personal laptop. You then question the $100 a month fee.

Bear in mind these laptops are likely to be $5000 or so because of the memory, HDD and M7 chip they likely need.

It feels to me like the beginning of the inflection point but software updates not hardware updates will be the accelerant.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by marci on Friday June 26, 2026 @05:57AM (#48684616)

  "That’s where EMO comes in.

  We show that EMO – a 1B-active, 14B-total-parameter (8-expert active, 128-expert total) MoE trained on 1 trillion tokens – supports selective expert use: for a given task or domain, we can use only a small subset of experts (just 12.5% of total experts) while retaining near full-model performance."
https://allenai.org/blog/emo
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by dainiusse on Friday June 26, 2026 @02:25AM (#48683030)
Curious, what exactly does it do for you? I has bad luck with these small models to do anything useful tbh.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by drnick1 on Friday June 26, 2026 @01:05PM (#48689017)
It's a voice assistant that can respond to commands such as "turn on the light," or explain things (within the abilities of the small model).
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by overfeed on Friday June 26, 2026 @01:47AM (#48682778)
> If it can do 90% of the tasks the big boys do, at 50% speed

I want to live in this world too, but these numbers, as of today, are very aspirational and far removed from reality.

I'm no tokenmaxxer; I find my modest local setup useful, I also know the limitations, it's slow and it sucks (relatively) at high-level and/or long-context planning, compared to frontier models. Only a minority of my prompts are max-effort - its not all I do, but, it also means frontier labs aren't dying any time soon

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by mikestorrent on Friday June 26, 2026 @02:13AM (#48682937)
Consider also that right now LLMs run slowly enough you can watch them think. I've seen a demo of an LLM running at an absurdly high speed and it reminds me of when I moved from a 2400 baud modem to a 14.4 - BBS screens that I could watch draw were all of a sudden nigh-interactive. Faster-than-realtime video generation is also coming, and will also continue to require huge hardware for a long while yet.

I love local models - I have a machine at home that runs a few for me and it's a lot of fun - but for the time being they are not super trustworthy on tool calls and staying on script. Another year or so might change all that!

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by ChickeNES on Friday June 26, 2026 @03:16AM (#48683380)
What does your local setup look like?
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by mikestorrent on Friday June 26, 2026 @08:29PM (#48693809)
1650 watts of liquid cooled Risc-V
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by KoolKat23 on Friday June 26, 2026 @04:34AM (#48683991)
If anyone wishes to see the future. A fast LLM is quite eye-opening. I think chatjimmy uses Talaas' chips where models are hardcoded into the silicon.

https://chatjimmy.ai/

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by calgoo on Friday June 26, 2026 @07:58AM (#48685604)
Yea, is almost "scary fast" in a sense... the amount of compute you can do in parallel one one of those chips is amazing. hopefully they get their next chip completed as that will be a lot more useful for general workloads. I think the current one is based on llama3.

*corrected llama version to 3

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by flyingjoe on Friday June 26, 2026 @04:56AM (#48684154)
Thanks, I didn't know that one! Very impressive speed although quality seems very bad
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by msdz on Friday June 26, 2026 @05:50AM (#48684566)
> although quality seems very bad

The weights they “etched” into the FPGA card that’s used for the ChatJimmy demo are that of a Llama 3-something 8b model.

The actually impressive and novel thing is that Taalas’ve managed to automate that process (clearly – nobody transforms 8 billion numbers into a physical representation by hand).

So now, they can work on scaling this process up, and with low enough lead times (I’ll be convinced they have inside connections to TSMC if they can actually deliver on the promised mere 3-4 months delay), will be able to offer 30-100b+ parameter models under half a year after they’re released, at thousands of tokens per second while probably drawing less wattage (per token, not sure about overall).

Exciting times ahead, folks.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by mikestorrent on Friday June 26, 2026 @08:28PM (#48693802)
At some point we're going to have these chips for a couple bucks in kids toys
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by kennywinker on Friday June 26, 2026 @03:13AM (#48683363)
I’m sure you’re right, for the things you are asking of an llm, just as I am right about the things I am asking of an llm.

The real question is, what are 90% of people going to ask llms to do. I’d argue mostly it’s going to be stuff that works-now or almost-works on local models, but that’s just an opinion. It also depends on the frontier models hitting a wall of steeply diminishing returns, since they set the expectations for all of this stuff - my gut says that’s happened already they just won’t admit it for a while - but we’ll see.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by SanjayMehta on Friday June 26, 2026 @02:56AM (#48683242)
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-focuse... by everfrustrated on Friday June 26, 2026 @03:17AM (#48683391)
The established AI players have no financial interest to make LLM available locally. They aren't hardware companies and if running LLM requires paying them to host the models as well then they can naturally capture more of the value chain = more revenue.

Apple is the only player here where it would play into their natural hardware incentive to get you to pay more for better hardware. It would make sense for them to find a way to run LLM locally (eg, newer architectures that others here have pointed out).

Interesting times.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rjzzleep on Friday June 26, 2026 @02:56AM (#48683245)
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.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by spiderfarmer on Friday June 26, 2026 @03:02AM (#48683275)
If we advance just 2x in hardware plus 2x in software, all coding can be done on local hardware imho.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rbanffy on Friday June 26, 2026 @03:59AM (#48683711)
That’s about 4 years in hardware cadence alone. There is a lot of room to improve memory bandwidth, and performance is a given with every process node. IBM has shown yesterday they can do limited runs on 0.7nm (density equivalent).
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by dgellow on Friday June 26, 2026 @03:15AM (#48683371)
The thing is, with the level of hard investment AI vendors have, even a small reduction of their addressable market is significant. They aren’t profitable, and inference is getting commoditized fast, so even if they eventually become profitable (not via financial engineering) they won’t be able to have good margin. The pressure of both open models AND local models is pretty bad imho
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by lumost on Friday June 26, 2026 @02:32AM (#48683080)
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-focuse... by nok22kon on Friday June 26, 2026 @03:51AM (#48683648)
if you do the electricity math you'll see that you pay more on local models while getting less (local is more heavily quantized) compared with OpenRouter.

I'm not talking local Gemma/Qwen vs cloud Opus, but against OpenRouter same Gemma/Qwen

there are reasons to run local - privacy, availability, but cost is not one of them

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by manarth on Friday June 26, 2026 @04:17AM (#48683869)
That's assuming consumption pricing remains as-is.

There has been a lot of market-subsidy in AI which is starting to fade away: e.g. the copilot quotas/pricing. When VC switches from investing to wanting a return, the price equation is likely to change.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by nok22kon on Friday June 26, 2026 @04:25AM (#48683934)
There is no subsidy on most OpenRouter providers, they are profitable today.

You buy a big GPU, you serve LLMs, you print money.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by brianwawok on Friday June 26, 2026 @07:50AM (#48685551)
And if you skip open router and go direct you save another 5%
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by JumpCrisscross on Friday June 26, 2026 @05:19AM (#48684323)
> do the electricity math

Could you give an example with real figures?

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by nok22kon on Friday June 26, 2026 @05:40AM (#48684484)
obviously depends on your location and GPU

for me it would be about $2 per day in electricity to generate 8 mil tok of Gemma4-26B at 4 bit quantization. this is excluding how much the GPU cost (no amortization)

ignoring the fact that I could get more free tokens per day for this model from Google/OpenRouter, it would cost $4 per day on OpenRouter if paid, but they would run it at full 16 bit precission

this would be the most "profitable" model for me

for Gemma4-31B I can generate only 1 mil tok per day, and so I pay more to get less quality than OpenRouter (ignoring that this model is also free on Google)

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by s1artibartfast on Friday June 26, 2026 @12:55PM (#48688904)
This is very interesting to me. How do you come up with the kwh/token for your setup?
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by nok22kon on Saturday June 27, 2026 @04:47AM (#48696391)
I know how many tokens per second my computer generates, and I have a wall power meter which measures how many watts my computer is using when generating.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by calgoo on Friday June 26, 2026 @08:08AM (#48685696)
I am allowed to plug in 800w of solar panels into a wall socket here in spain. That would more then cover my current computer with 16gb vram. Now if i went and built a LLM server, at full load i would probably be closer to 3600w (Dual Epyc CPUs that gives you 8 x16 PCI channels and up to 8 cards - Way overkill, i know). If i half that with 1 EPYC and 4 x16 PCI channels, and add the same amd 7800xt i currently have then i should in theory be able to run at around 1800w under full load. Now that could still be covered with a 2000w solar install (get a professional setup OR get a battery unit like a EcoFlow that can output 2000w and can input about the same amount of solar).

Now, this all brings the upfront costs way up, the solar panels are cheap, its all the rest around them that tends to cost money.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by re-thc on Friday June 26, 2026 @03:57AM (#48683695)
> 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.

Benchmarks maybe? Real world, no.

You just need the context otherwise. There's no way around it.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by lumost on Friday June 26, 2026 @07:34AM (#48685420)
Context is more available locally. You can have the LLM operate for arbitrarily long periods, use your credentials to access services (if desired), store memory locally etc.

Whether such a model exists or not is a different question.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by wisty on Friday June 26, 2026 @03:03AM (#48683289)
I'm not paying for a super computer to do my taxes if a cheap pc can do it for free.

So yeah, commercially it might be a death knell. Yes there's still a market for super computers, but would your rather own Apple or Cray?

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rbanffy on Friday June 26, 2026 @04:04AM (#48683745)
> would your rather own Apple or Cray?

I would consider an HPE tower server with a processor on the same league as an M6 or M7 under the Cray brand.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by interludead on Friday June 26, 2026 @04:00AM (#48683722)
I think this is right but it also depends on what "compete" means
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rubyn00bie on Friday June 26, 2026 @12:59AM (#48682498)
We'll likely see a transformation in how frontier models are trained as a result of a push towards local inference. While it seems unlikely now, given current pricing for RAM, in 10-15 years it's not unthinkable to assume we could see individual machines with 10-12TB (and well beyond that) of RAM which are accessible to the GPU. Min/max system RAM increased a LOT from 2010-2025 and largely because it was cheap. Once the hyperscalers aren't generating revenue for the RAM manufacturers, I wouldn't be surprised to see a massive push towards consumers in order to maintain gross profit. Not to mention new players who enter the market because the margins are measurably absurd right now.

At some point there will be diminishing returns towards the "just throw more RAM at it" approach the current frontier models are taking. Commoditization is just as inevitable as it ever was... and in doing so will enable actual leaps of what AI/ML is capable of. That's not to say there won't be a place for 99.999999% accurate vs 99.99999% but those cases will be limited and likely prime to disruption based on real innovation vs access to capital.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by Culonavirus on Friday June 26, 2026 @01:56AM (#48682828)
The 1080ti is out there for almost 10 years now. It has 11GB of VRAM. A 5090 has 32GB.

SOCs with unified memory have shifted this a bit forward, but they're also expensive as shit.

10TB ram in a consumer device is simply not happening in the next 10 years.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rjzzleep on Friday June 26, 2026 @02:57AM (#48683249)
Half a year ago you could get a AI max 395+ with 128GB ram in mobile form factor for ~$2200. The same thing costs $3700. Same SoC, same memory.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rbanffy on Friday June 26, 2026 @04:08AM (#48683782)
10TB is about 80 times that, 200K in today’s money. A lot of capacity is coming online in the next 5 years and it’s reasonable to think we can get there with better process and stacking (the latter does little for pricing, but enables shorter latencies).
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by jpc0 on Saturday June 27, 2026 @04:25AM (#48696283)
> A lot of capacity is coming online in the next 5 years

Is this true though? I don't really have time to do the research and have no dog in the race but I'm sceptical...

But then again I'm not there one making our profiting from the claims that there is billions being invested into infra...

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by interludead on Friday June 26, 2026 @04:04AM (#48683744)
I agree with the general direction but I'm a little skeptical of the "just add a few more TB of RAM and the frontier moves local" version of it
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by bitwize on Friday June 26, 2026 @01:26AM (#48682643)
Indeed. Local models becoming available and halfway decent don't obviate the laws of scale. And because there's no ceiling to what scaling more will buy you in terms of capability, there's no reason not to scale more, there's no incentive for billionaires not to grab all the fab capacity they can.

Enjoy paying $1000 or more for a little 4 GiB cloud terminal that connects you to all your online accounts where all your actual work gets done. This is the future.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by colechristensen on Friday June 26, 2026 @01:50AM (#48682795)
>there's no ceiling to what scaling more will buy you in terms of capability

This is highly doubtful.

Rule of thumb: everything people think is exponential is actually an S curve.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by nok22kon on Friday June 26, 2026 @03:57AM (#48683700)
better rule: exponentials are overlapping S-curves
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by bitwize on Friday June 26, 2026 @03:49AM (#48683634)
There's a limit that won't be breached without a fundamental breakthrough in physics of computation, but we're not there yet by a long shot. You can train bigger models, faster, and infer with them faster and more precisely, by throwing more compute at the problem for the foreseeable.
Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by rbanffy on Friday June 26, 2026 @04:11AM (#48683808)
At some point, and I can already see it, they’ll be better than us at writing code. We are still in the loop to coerce them into architecting well, but that’s nothing magical.

What’s frontier now is prosumer in a couple years and commonplace in a couple more.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by AnthonyMouse on Friday June 26, 2026 @07:08AM (#48685216)
> Hardware that can only run quantized models that take up GBs in VRAM

That's the today hardware.

Now suppose Apple goes to any of Samsung/Micron/Hynix and says "we'll pay you the entire cost of building another DRAM fab and in exchange we want its entire output" and then releases M7 devices with enough memory and compute to run bigger models.

> Unless Apple surprises everyone and brings back the XServe with M7, if not, then laptop and desktop for factors simply can't dump heat fast enough to compete head-to-head, and will be designed for lower input wattage.

Laptops maybe. Desktops can dissipate more heat than the amount of electricity you can draw from a typical household wall outlet.

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by overfeed on Friday June 26, 2026 @10:12AM (#48686852)
> Now suppose Apple goes to any of Samsung/Micron/Hynix and says "we'll pay you the entire cost of building another DRAM fab and in exchange we want its entire output"

It's revealing that they aren't doing this: no one wants to fund that gamble on the state of AI demand 12-18 months out, but ate happy to capitalize on their current product lines/capacity.

> Desktops can dissipate more heat than the amount of electricity you can draw from a typical household wall outlet

100% agree, but the data center power and cooling infra are not limited by home wiring, and go way beyond what a wall outlet can safely provide (1,440W max on a typical 15A circuit at 120V). A single H100 maxes out at 700W

Re:Apple to skip high-end M6 Mac chips in favor of AI-focuse... by AnthonyMouse on Saturday June 27, 2026 @04:59PM (#48701706)
> It's revealing that they aren't doing this

They are doing this. All three of the DRAM manufacturers are actively expanding capacity. It's just not an instantaneous process.

> 100% agree, but the data center power and cooling infra are not limited by home wiring, and go way beyond what a wall outlet can safely provide (1,440W max on a typical 15A circuit at 120V). A single H100 maxes out at 700W

A desktop with the performance and the 160GB of VRAM of two H100s would sell like hotcakes. The power consumption is also largely proportional to the amount of compute rather than memory, and can be significantly improved by using lower clock speeds and then either making up for it with wider silicon or just not caring that it can run the same model but is e.g. 25% slower than hardware that uses twice as much electricity.