Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

Apple could probably sell a machine starting at $10,000 if they architected it as the sole place one’s private cloud AI compute ran on.

It would need a path to a $2,500 machine. But this is a niche I don’t think another consumer-facing brand could do like Apple.

What I’m not sure to understand is that if you want to just run Claude code or openclaw type software with llm apis or subscriptions (and not run local models) to benefit from a local file system and always-on capability for ‘second brain’ type of workflows, I guess you don’t need a Mac mini but can run it on a raspberry pi or an old laptop ? Does anyone have experience with that ?

If I had the capital I’d make an household inference appliance.

No peripherals except Ethernet, integrated compute (cpu+gpu+mem) and secondary storage (+mobo, psu). No accoutrements, just the minimum amount of hardware to run a model as a utility.

Even the appliance faceplate would be a display showing stats like an old HiFi stereo.

Edit: something like a series of modules consisting of a RISC-V CPU + Vortex GPGPU + memory

Running models on-device on a Mac is immensely annoying though. Figuring out what will work out of BF16, FP8, BF16+FP8, NVFP4, INT8, GGUF ... the list goes on ... is 'non-obvious' at best. Apple do little to support with tooling. There's MLX, but unless you're happy to transform a model to that format yourself you'll be lagging a long way behind.

Apps like LMStudio, Ollama, Draw Things, etc do a great job of simplifying it but it's still a pain.

It’s not for the AI inference, it’s for the tool calls and desktop GUI app workloads and browser. There aren’t any on-device models capable enough of real work that can run on lower end Mac Minis. But for running a few browsers and GUI apps, you’re much better off buying a Mac Mini than paying for a more expensive and worse-performing container in the cloud. Browsers were not designed to run in Linux containers but they run optimally on baremetal desktop OSes. An M4 Mac Mini beats the single core performance of any VM you might rent in the cloud, in terms of raw compute per dollar (Geekbench scores).

> Apple's Mac mini and Mac Studio have become the machines of choice for running AI agents, according to Doug Brooks, Apple's senior product manager of Apple silicon.

This is mostly an US phenomenon, no Mac mini nor Mac Studio around here.

Only Thinkpads and Macbooks laptops talking to hyperscalers.

> "people often want a system that's under their control, isolated from their primary machine, and capable of running 24 hours a day, seven days a week," said Brooks. "A Mac mini is an amazing system for that," he added.

These execs are so out of touch they believe Apple hardware to be "a system that's under their control", how does it come to this? Besides, a VM without bi-directional sharing of data gives you pretty much the exact same thing.

Did hundreds/thousands of developers really go out there and bought Mac Minis just because one prominent technology semi-celebrity happens to have used a Mac Mini for the development of their thing? Seems bananas people would spend hundreds on monies on something they barely grasp how it works.

Ok, I didn’t want to take the bait but this one’s just too much.

> “He also described a shift toward running AI locally rather than in the cloud – a move motivated by privacy, security, and the rising cost of inference as agents consume more tokens.”

Classic Apple. No more just beating the “security and privacy” drum, now its “tokens are expensive!”

<neanderthal voice/> Cloud scary. Cloud expensive. Mac good. Buy Mac!

> “He also singled out what he calls ‘transparent AI’ on iPhone and iPad, referring to features scattered throughout the operating system and third-party apps that work quietly without announcing themselves as AI.”

<neanderthal voice/> Apple use AI, Apple just not say it. Apple smart, not lagging behind industry! Buy iPhone!

How about you invest in developing your own models, correctly? And provide a secure and private inference cloud service on your fancy Apple silicon? And integrate that into your platform so Siri gets smarter without you farming queries out to Google Gemini? Bill me for it in iCloud+ I’ll probably pay for those tokens.

Was that so hard?

People bought diesel cars as miles per gallon was higher than petrol.

People are buying apple unified as electricity costs in many countries are very high, so cheaper to run than Nvidia setup.

As non-apple unified memory options increase, many people will have more choose those

The issue with the Apple is that they didn’t really develop any competitive local AI machine. Their strategy/marketing falls flat when you ask them how exactly they implement AI: they buy it from Google cloud. In the future local AI may become a thing but that’s 4-5 years away. I count the 2q-4q and atrocious performance as “local ai” only for the enthusiasts crowd not for people doing competitive work.

Apple could dominate this niche if they decided, for a while until prices fall, to eat some margin and bump up RAM in high end models. Couple that with a new M series chip with even faster AI performance.

It’s not a huge niche but it’s an influential one. They’d get the engineers and CXOs of AI ventures and a lot of academics and hobbyists.

For the platform it would keep them cemented as the high end vendor. In the long term it would position them to take advantage of any software or training breakthroughs that deliver frontier model performance at that scale.

I don’t understand why they are not reintroducing the Apple Xserve?

Being a Mac switcher since 2003 I am as much of a fanboy as anybody else but this quote from the article caught my attention, and smells like PR.

> Many AI tools are also Mac-first or Mac-only

I fail to recall AI tools Mac-only general purpose AI or agentic tools. Most of the claws, harnesses, studios and inference engines seem to be multiplatform. You can say you can run then in a Mac with a nicer UI wrapper or whatever, but "Mac-first" or "Mac-only"?

Apple doesn’t have an ads business, and it is inevitable that Google/openai/Anthropic are going to seek to monetise consumer ai via ads.

So the ad free Apple on device experience will be welcome.

Oh please the neural engine is mostly useless for LLMs. Siri in iOS 27 is laughably pathetic and slow compared to GPT Live DESPITE sending personal context to their (attested) cloud to execute anything but the most basic queries. Still years behind.

> "The speed of AI development right now is just crazy," Brooks said. "I can't imagine where we're going to be a year from now, three months from now, or even a month from now," he added.

I don't think I'm taking this out of context when I say this is unintentionally correct. Apple still doesn't know what to do about AI.

Luckily, it doesn't matter because it's a solution in search of a problem. Most consumers aren't using AI apart from google search.

Everyone else is using it as a content scraper and praying nobody will step in to end the piracy/fraud.

Apple could probably sell a machine starting at $10,000 if they architected it as the sole place one’s private cloud AI compute ran on.

It would need a path to a $2,500 machine. But this is a niche I don’t think another consumer-facing brand could do like Apple.

The out-of-stock $6000 M3 Ultra Mac Studios with 800GB+ memory bandwidth are going for $24,000 on eBay, so yes definitely

If I had the capital I’d make an household inference appliance.

No peripherals except Ethernet, integrated compute (cpu+gpu+mem) and secondary storage (+mobo, psu). No accoutrements, just the minimum amount of hardware to run a model as a utility.

Even the appliance faceplate would be a display showing stats like an old HiFi stereo.

Edit: something like a series of modules consisting of a RISC-V CPU + Vortex GPGPU + memory

Isn't that what what George Hotz is doing over at tiny? https://tinycorp.myshopify.com/

You're describing the mac mini/studio with some facelift.

Is that the nvidia spark?

build a Xeon / epyc 4u server. 12 channel ram.

Apps like LMStudio, Ollama, Draw Things, etc do a great job of simplifying it but it's still a pain.

I dunno I use LMStudio pretty regularly and the MLX folks and the community usually have MLX versions of new model releases up within a day or two.

At their original price points, a set of four were a great solution for my requirements in tokens/second/$.

Ok, I didn’t want to take the bait but this one’s just too much.

> “He also described a shift toward running AI locally rather than in the cloud – a move motivated by privacy, security, and the rising cost of inference as agents consume more tokens.”

Classic Apple. No more just beating the “security and privacy” drum, now its “tokens are expensive!”

<neanderthal voice/> Cloud scary. Cloud expensive. Mac good. Buy Mac!

<neanderthal voice/> Apple use AI, Apple just not say it. Apple smart, not lagging behind industry! Buy iPhone!

Was that so hard?

But why should apple invest in developing their own models? Why would it be correct?

Or phrase it in a very similar ask, why don't they invest in power plants? The model space is truly crowded, what do they gain or recover suppose they are SOTA? Across the Pacific they are pumping out free models that are only 6-12 months behind. What business sense does it make for Apple to develop their own models?

Being a Mac switcher since 2003 I am as much of a fanboy as anybody else but this quote from the article caught my attention, and smells like PR.

> Many AI tools are also Mac-first or Mac-only

build a Xeon / epyc 4u server. 12 channel ram.

At their original price points, a set of four were a great solution for my requirements in tokens/second/$.

But why should apple invest in developing their own models? Why would it be correct?

They don’t believe in this model and never had. You sound like the people who screamed that Apple was dying because they were not making a netbook style Mac in 2009. Apple is the only big tech company with a non existent financial exposure to the current capex bubble. Let big dogs bark at the moon. They are the loud ones, at least until the moon implodes.

I don’t understand why they are not reintroducing the Apple Xserve?

Target audience - B2B. There are multiple videos of Steve Jobs saying that he hates B2B, because the people using the devices are not the ones making the purchasing decision. It is pretty much against Apples DNA, and all their B2B they have today is a means for them to sell more B2C.

My guess is the OS. People who want a server often enough want to choose the OS, Apple wants to supply the OS and the hardware together so they're not blamed every time the two turn out to be incompatible, as happened the other way round in the 90s.

> "The speed of AI development right now is just crazy," Brooks said. "I can't imagine where we're going to be a year from now, three months from now, or even a month from now," he added.

I don't think I'm taking this out of context when I say this is unintentionally correct. Apple still doesn't know what to do about AI.

Luckily, it doesn't matter because it's a solution in search of a problem. Most consumers aren't using AI apart from google search.

Everyone else is using it as a content scraper and praying nobody will step in to end the piracy/fraud.

> Luckily, it doesn't matter because it's a solution in search of a problem. Most consumers aren't using AI apart from google search.

This is... a view.

Maybe I live in a strange sphere of strange ("normie"-ish) people, but the people around me are for sure using AI. Mostly chatgpt to be fair. They use it to compare products that they intend to buy, identify plants in nature, create travel plans, find interesting places to visit nearby, give movie suggestions based on what they have previously enjoyed and so on and so forth. AI is becoming a very integrated part of their reality. To "google" something and digging through the search results manually is very rapidly being replaced by asking chatgpt, for better or worse.

Nobody does what to do, they are just throwing trillions at it betting they’ll figure out. If they don’t they’ll be screwed, if they do Apple will quickly catch up with a better and more refined product, as they’ve always done.

The new Siri isnt that exciting at least on my iPhone 15 Pro Max. I know it's beta but it's sluggish and often says try again. I watched many videos on Youtube saying its amazing but maybe not so much on older phones? Also, I need a Siri I can talk in an unfettered manner from my lock screen while Im driving without having to unlock the screen. Probably a big ask for Siri to know my voice via voice fingerprint allowing unfettered access from my lock screen.

Others running the beta now on newer iPhones and enjoying it more so?

The out-of-stock $6000 M3 Ultra Mac Studios with 800GB+ memory bandwidth are going for $24,000 on eBay, so yes definitely

I don’t think we should use current prices as landmarks for large scale demand. That Studio’s current prices is inflated because of a (presumably) short term supply crunch, not because the average user is willing to pay $24k for a home AI inference device.

It assumes that RAM remains supply constrained and that none of the existing RAM contracts are cut short.

But Meta and xAI putting A TON of AI compute onto the market. OpenAI and Anthropic are raising the costs of inference (by reducing how much inference users get via subscriptions). And we haven’t seen Oracle / CoreWeave struggle to pay their debts yet, but they will be selling assets once they get close to that point.

Let me clarify, I think Apple could sell a device at the scale Apple sells at around the $10 to 25 thousand price point.

Like, take out the price sheets for the Apple Car. Then sell me an AI tower at those price points.

Isn't that what what George Hotz is doing over at tiny? https://tinycorp.myshopify.com/

Yes, but for inference. 45k is so far out of the budget of a professional unless you earn ridiculous money and have no dependents.

You're describing the mac mini/studio with some facelift.

Absolutely, but not under the control of Apple.

Yeah but like running linux hopefully

Is that the nvidia spark?

Yes, and a lot of others.

A bit too expensive for a home appliance though, isn't it?

I dunno I use LMStudio pretty regularly and the MLX folks and the community usually have MLX versions of new model releases up within a day or two.

For some models like the popular coding and chat models, things move faster. For things like images, voice, sound etc they definitely lag a long way behind.

& they clearly delineate all the models that’ll work on your exact machine (but guardrails can be disabled in settings)

It assumes that RAM remains supply constrained and that none of the existing RAM contracts are cut short.

Yes, but for inference. 45k is so far out of the budget of a professional unless you earn ridiculous money and have no dependents.

Absolutely, but not under the control of Apple.

Yeah but like running linux hopefully

Yes, and a lot of others.

A bit too expensive for a home appliance though, isn't it?

For some models like the popular coding and chat models, things move faster. For things like images, voice, sound etc they definitely lag a long way behind.

& they clearly delineate all the models that’ll work on your exact machine (but guardrails can be disabled in settings)

apple has invested in training models

https://machinelearning.apple.com/research/introducing-third...

they just suck

> Luckily, it doesn't matter because it's a solution in search of a problem. Most consumers aren't using AI apart from google search.

This is... a view.

Chatgpt is so damn good for cooking it is unbelievable. It will learn your family's tastes over time, you can tell it what pantry staples you keep is stock, and you can take any recipe you find online and ask for stuff like "find a way to make this preparable in 45 minutes instead of 2 hours, what trade offs will I be making?"

This is true but I can do the same on free ChatGPT without even logging in. I wouldn't pay $5 a month for that functionality, much less $20 (or >$1000 to be able to run it at home).

SOTA AI for "serious" work is in a different position, used by fewer people but with big pockets and sometimes a pathological dependence on it.

Others running the beta now on newer iPhones and enjoying it more so?

> The new Siri isnt that exciting at least on my iPhone 15 Pro Max

On my Pro 16 it has its ups and downs - I still can't get it to "play my running playlist on shuffle" whilst running (this is the only thing I used Siri for before the beta and it would improve my life immeasurably if it worked). But it responds to things like "how long will it take to drive to the AirBnb booking in my inbox", and "when is X playing a concert in Y - add a calendar entry with details" perfectly.

This is a beta and I have hopes, but I can imagine it will run better on a 17 and later

I use it on my 15 pro max. It's a major improvement, but I still don't use siri much. It's gone from murderously infuriating to passably usable. I still use gpt for any sort of exploratory conversations. I haven't bothered trying to use siri for that because to me that's not what siri is for.

Although given how effed up the voice for chatgpt is now with the latest updates I might talk with siri more.

Because I use carplay in tandem with my phone where the map is on the carplay screen and turn by turn directions are on my phone, it's always unlocked so I haven't run into whatever lock screen issue you brought up.

The best models for new Siri, on device, requires the iPhone 17 Pro, so your experience on a 15 is going to be degraded.

Let me clarify, I think Apple could sell a device at the scale Apple sells at around the $10 to 25 thousand price point.

Like, take out the price sheets for the Apple Car. Then sell me an AI tower at those price points.

In 2010 one of the standard configurations for the Mac Pro was $4,999. Once you customised ram, storage, peripherals and software it could easily end up above $15,000, or $23k today accounting for inflation. Apple hardware is one thing that has actually got cheaper over time.

https://www.macworld.com/article/209019/macguide2010.html

Or they could use that same amount of memory to ship 64x Macbook Neos, and probably make higher margins off the hardware volume.

Those Macbook Neo users would be very reliant on Apple intelligence, enough maybe to pay for a service with it. I think Apple's much happier going this path.

I’m still disappointed they didn’t make a Mac Pro with 4 or 8 or 16 or 32 ultra M chips for something insane

apple has invested in training models

https://machinelearning.apple.com/research/introducing-third...

they just suck

This is true but I can do the same on free ChatGPT without even logging in. I wouldn't pay $5 a month for that functionality, much less $20 (or >$1000 to be able to run it at home).

SOTA AI for "serious" work is in a different position, used by fewer people but with big pockets and sometimes a pathological dependence on it.

Although given how effed up the voice for chatgpt is now with the latest updates I might talk with siri more.

> The new Siri isnt that exciting at least on my iPhone 15 Pro Max

This is a beta and I have hopes, but I can imagine it will run better on a 17 and later

The best models for new Siri, on device, requires the iPhone 17 Pro, so your experience on a 15 is going to be degraded.

https://www.macworld.com/article/209019/macguide2010.html

Or they could use that same amount of memory to ship 64x Macbook Neos, and probably make higher margins off the hardware volume.

Those Macbook Neo users would be very reliant on Apple intelligence, enough maybe to pay for a service with it. I think Apple's much happier going this path.

I’m still disappointed they didn’t make a Mac Pro with 4 or 8 or 16 or 32 ultra M chips for something insane

I agree! I think it's because there's so much cooking material in its training data. I wonder what proportion of the internet is food blogs and recipes... Probably a lot!

People bought diesel cars as miles per gallon was higher than petrol.

People are buying apple unified as electricity costs in many countries are very high, so cheaper to run than Nvidia setup.

As non-apple unified memory options increase, many people will have more choose those

The remote access story for macOS is absolute sadness, without Jump Desktop there would be zero performant ways to access that “system under my control”.

And all of that because Tim Apple fears any feature that could mean people could have less than one iDevice per person.

I think tech people spend hundreds on tech because it’s fun.

It’s not a huge niche but it’s an influential one. They’d get the engineers and CXOs of AI ventures and a lot of academics and hobbyists.

Yeah I find the Mac mini trend is kind of baffling.

It seems like it's driven either by 1) people hearing Macs are good for AI, buying one, and using Claude for inference, not realizing that you interact with the anthropic API from an internet connected hair dryer. Or 2) people want their agents to have blue bubbles.

I find it hard to believe that enough normal people are doing on device inference is driving Mac Mini's out of stock. And even if they were the Mac mini is not actually a very good platform for it.

You don’t need a Mac Mini just for that, but they’re fairly inexpensive (or were anyway) and quality is very good. The people who buy them may never use all the performance available, but they’re more interested in convenience than getting the cheapest thing possible.

You can sort of justify it by assuming it will last a long time and they’ll use it for other things, too.

it's only because you can send texts via imessage on a macmini. that's it.

Correct. You do benefit from some headroom for things like launching browsers etc but refurbs or mini PCs (with at least 16gb; ideally 32gb of memory) from the likes of Minisforum or GMKTec work well enough if you're wanting to spend a little bit of money.

Yup, for openclaw and APIs you dont need a big PC. I run something lightweight on the RPI4 8gb. Many people run local LLMs which is where a mac is useful. Frankly I dont think you can beat the value of an openrouter subscription and API calls.

Pretty much. Running a local harness calling an llm via APIs doesn't necessarily take a lot of resources. But whatever tasks you want that agent to do via tool calling will be limited by the resources of the machine it runs on if you run those locally, so that's what should inform your choice of specs in this case

I do exactly this. You can run the whole thing on a PI. I have actually installed asahi Linux on my Mac and I connect to it remotely so you can be sure I will never upgrade my Mac again because it’s already overbuilt.

...or any cheap VPS? I now do most of "second brain" things via pi harness with Opencode Go subscription, and it costs me like 20 bucks a year, with added benefit of "you can have tmux and open session realtime on whatever device".

> Apple's Mac mini and Mac Studio have become the machines of choice for running AI agents, according to Doug Brooks, Apple's senior product manager of Apple silicon.

This is mostly an US phenomenon, no Mac mini nor Mac Studio around here.

Only Thinkpads and Macbooks laptops talking to hyperscalers.

Apple doesn’t have an ads business, and it is inevitable that Google/openai/Anthropic are going to seek to monetise consumer ai via ads.

So the ad free Apple on device experience will be welcome.

Around where? They're pretty popular for it in the UK right now given our obscene energy pricing as they end up being one of the best low power options for local llm. If you're not in the local llm space you obviously wouldn't see it. It's like saying Tennis isnt popular around here then admitting you dont frequent a tennis court so wouldn't even know.

Welcome to the ad-filled experience, we think you’ll love it. – Tim Apple

https://ads.apple.com/maps

What does this mean? Apple ads bring in 8 billion revenue a year.

I think tech people spend hundreds on tech because it’s fun.

The remote access story for macOS is absolute sadness, without Jump Desktop there would be zero performant ways to access that “system under my control”.

And all of that because Tim Apple fears any feature that could mean people could have less than one iDevice per person.

I'm curious what you mean. I have been accessing Macs remotely over SSH and VNC for like 20 years and it's always been easy and as performant as the network would allow.

You can sort of justify it by assuming it will last a long time and they’ll use it for other things, too.

Yeah I find the Mac mini trend is kind of baffling.

I find it hard to believe that enough normal people are doing on device inference is driving Mac Mini's out of stock. And even if they were the Mac mini is not actually a very good platform for it.

One aspect you're missing is that people running a claw type agent thing need to run it on a Mac to automate software in the Apple ecosystem.

Neo-Siri in iOS 27 removes the need for a lot of this, but before then, if you want to ask a robot about information that is stored in Apple notes, or to send an iMessage, a Mac mini is your only practical option.

The demand is not coming from 'normal Apple customers' it's coming from people who want a machine that can run local AI.

It has nothing to do with Macs being especially good at AI. It has everything to do with being one of the last 'cheap' devices being sold with that much unified RAM.

The people I know getting Mac Minis to run agents (I include myself) are running local LLMs.

There are two angles to this. One is that if you want to integrate your agent setup into the Apple ecosystem you need a network connected Mac running 24/7.

The second is that the puck is heading towards local models. The people running their own 'Claws are usually experimenting running their own services either to save money or to explore the future where 95% of requests are handled on device.

I assume people ask an LLM what to use to run locally, and it suggests a Mac mini

I believe it was because it allowed OpenClaw to access iMessage directly

it's only because you can send texts via imessage on a macmini. that's it.

Buying a new computer at +$500 just to have iMessage access feels insane to me.

OpenClaw supports all the mainstream (and free) chat apps like Discord, WhatsApp, Signal, Telegram... None of them requiring a MacOS machine.

Is it a lack of knowledge from the users or do they really value iMessage integration that much?

Not even. It's literally "yeah bro, you gotta get a Mac Mini".

Welcome to the ad-filled experience, we think you’ll love it. – Tim Apple

https://ads.apple.com/maps

Around here in my German office, and down in my home country Portugal, even less, given the average salaries.

So, when you said pretty popular, you meant in the local LLM space, which is a niche of a niche.

What does this mean? Apple ads bring in 8 billion revenue a year.

I'm curious what you mean. I have been accessing Macs remotely over SSH and VNC for like 20 years and it's always been easy and as performant as the network would allow.

They aren’t as aggressive and focus on the customer experience more than others, 8bn isn’t a lot for a company with their reach.

For example Apple radio is a free product with no ads, Apple TV and Apple Music don’t have an ads supported tier.

Advertising accounts for about 1% to 2% of Apple's total overall revenue, bringing in roughly $8.5 to $12 billion annually.

1-2% is rounding error.

If you or anyone else don’t mind, I have a have a question or 2.

I use Claude Pro ($20/m) as a glorified search engine (no ads/SEO) plus simple hobbyist dev things (shell scripts, managing my Mac, apps etc.

I also use it for tasks like - “search the web for top ten selling EVs, put them in a table” and then iterate - pivot tables, charts, additional research”. It could be cars, it could be broccoli. Code Work has facilities to streamline this type of work, but I usually drop into the CLI.

How much if any functionality would I need to recreate if I switch to OpenRouter and would be match my costs with the API approach. I don’t want any cost overruns. With Codex or Claude, if I run of tokens, no big deal, I can wait.

Thanks!

> Many people run local LLMs which is where a mac is useful

Unless you go for the very expensive options, most of the Mac Minis really aren't suitable for running local LLMs, they're painfully slow with prefill/processing input, and the models you are able to run don't handle long context very well, which these sort of long-running agents perform very differently with when you can.

I'll agree with your latter point, hard to beat the value of using something like OpenRouter or similar remote inference.

Even with local models, you can run the agent software and the inference workload on different hosts, which is what I'm doing at home. Beefy server responsible for inference, tiny VM on other server is running the actual agent software + RPC + bridges and what not.

Why not go direct to the source instead of paying an extra 5.5%? Seems like it'd be trivial to have AI wire up connections to your preferred inference providers and save yourself some money over time.

The built in high rez screen sharing between Macs works well too. Through Tailscale I’ve accessed my main Mac from both the opposite coast of the US and from the other side of the Pacific and it works great.

Host resolution automatically matches that of client, image quality is great, framerate is decent, latency is minimal. The host creates virtual screens for the connection so connected screens don’t light up and the machine remains locked to anybody accessing it physically too, which is a nice privacy assurance.

One aspect you're missing is that people running a claw type agent thing need to run it on a Mac to automate software in the Apple ecosystem.

What does the new Siri do that circumvents the need for a mac? To access Siri you still need one no?