Not exactly "future proof" for >1T parameter models but good for targeting specific lower-parameter models, or if you can rely on pipeline parallelism and run a cluster.
Wow, "Local AI" mentioned in the subheading above the fold - it's really awesome to see Apple leaning into this use case and I think it will definitely pay off for them going forward. Fingers crossed Apple is able to put some engineering effort towards shipping with one of the frontier open weight models included and optimized exactly for the machine.
For a non-quantized Deepseek V4 flash on an ultra, I would estimate about 1000+ tokens per second prefill and 50+ tokens per second on generation. This is actually quite usable and near parity to cloud.
They mention "adds the GPU Neural Accelerators." which, if exploitable for LLM loads, would probably help the prefill a lot
"Storage performance is up to twice as fast, with a next-generation SSD architecture built on PCIe Gen 6..."
This is the first personal computer I've noticed that has PCIe Gen 6 storage. I've only seen enterprise PCIe Gen 6 SSDs up until now. Gen 5 SSDs in consumer devices already have high temperatures and thermal throttling, so I'm worried about how Apple's implementation will perform (I know they don't use off-the-shelf SSDs anymore, but I'd imagine the temps would still be a problem).
Apple also launched the base M6 today with a 32GB RAM limit, suggesting 512GB may remain the maximum for Ultra chips for some time. Since these Ultra chips combine 16 base chips:
32GB × 16 = 512GB
I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.
Maybe $17k for a 512gig system that can do 1.2TB/s seems like a pretty good deal for a small office.
Ugh. I was waiting it out on a very old Mac, but the pricing these days is insane, so now to wait it out for at least two years more and hope for better pricing or just suck it up and pay a lot for less.
I may consider a M6 Mac Mini as a stop-gap whilst waiting out RAM Apocalypse to be over. Basically abandoning any ambitions of AI sovereignty and riding out subsidised LLM pricing for the next couple of years.
I can't hate a direction where Apple becomes more about building great computers rather than trying to force more and more subscriptions. I do wish they would fix many of the long-standing OS and native app problems.
I'm glad they brought the 512GB option back.
Really want to get my hands on a m6 32GB 2TB model but don't really have a need for one.
I know there's tons of marketing language, buzz words and attempts at convincing me of some agenda that isn't super clear without lots of effort in "validating" the slop. I guess its not bad "slop" though if a human put in effort in editing it (imo >50% human curating = not really bad ai slop)
Though I still would prefer I could just get the prompt. What human thoughts, direction and "prompt" went into writing this article? in the same way as we ask for the prompt for AI generated outputs, I would prefer it for human generated output too. For writing at the least. I could have saved time, got the purity of the argument, and got more clear information. I wonder if we can get a future where humans just express their intent with each other and stop trying to hide our agenda; I want a world we can trust each other greater and interpret and act on our goals without the noise of trying to impress or market to each other & the additional words that go into that.
We make a lot of price/performance compromises for having an attached screen and keyboard on our computer. That was what got me started.
Then I remembered the days of having to go to a special corner of the house to use a computer, vs now when I have a computer with me all the time. In my bag, on the sofa, on the train. Hell, I'm writing this on the work MBP while waiting for an appointment.
And you know what, I think I got more done when I went and sat in a corner of the house all those years ago. I set up an area for "computer work", and it worked really well.
I have a home office, but it's a jumble of cables going into docking stations and all sorts of weird stuff. I think if I streamline it and turn it into a proper "computer room", I might get some of that mojo back. I might even convince my partner that surrendering the home office and having a corner of the den might be good - she can watch TV while I tinker. And I won't be balancing a laptop on my knee and trying to do two things at once.
And the price/performance thing comes back in. Hmm.
HPSS works well via 5G, and Tailscale is incredible for the setup as much as the hardware.
Edit: I ended up getting a 15" M5 Air but honestly trying it on a 13" M4 Air was actually superior because when all you care is mobility (since the Studio does the heavy work) its nice just going around with almost no weight / bulk.
E.g. what most major tech companies have - a laptop that is for VSCode via ssh/web browsing, and a beefy Linux dev box you ssh into for everything else?
It's way cheaper, and what I use at home too - a lot cheaper than a Mac studio for everything, especially with RAM and storage.
I was always cobbling together ad hoc network access, to get from one machine to another. Access to my Mac Mini while traveling was a pain. Bringing it with me is ridiculous, and network access was a PITA.
Tailscale is wonderful magic. Free (for my usage), so easy to set up, and now no matter where my various computers are, they are all accessible trivially via a single ssh connection.
So get a beefed up desktop Mac, set up Tailscale, and then use any random laptop, anywhere, to use it headless.
Isn't 170GB/s slow for bandwidth?
Personally, I can't justify dropping the dosh for a 512GB M5 Ultra, but I would be able to justify it to myself if I could get 1TB of memory, because it'd guarantee the flexibility with local models I currently am missing. Seems a huge miss to not offer this... for a price.
Most people at Apple have already realized that their processors are already too powerful for regular users - heck, as a developer my M2 Pro with 32 GB RAM is more than enough for me.
Regular users don’t care about local AI either. So, they will probably extract as much money as possible during AI gold rush, but then we will most likely see Apple
a. Making their software worse (god forbid, forced updates)
b. Making their hardware impossible to repair (as they almost accomplished this already) and easier to break.
They gave me a nice MBP for my new job. I tried doing heavy work on it locally, it was fine for that, and yet it still ended up being a light terminal into an EC2 instance, partially because their stuff is on AWS and latency is way lower within that. My personal mini is running too.
In many ways, the Mac Studio is the spiritual successor to the trash can Mac Pro. Apple Silicon's architecture solved the thermal problems that limited the trash can Mac Pro.
You can't upgrade the processor because it's soldered. You can't upgrade the ram because it's soldered. You can't upgrade the SSD because it's soldered / bonded to the CPU. You could maybe have some PCIe slots, but not many drivers for macOS, so what's the point?
Yes, it was different in the old days, but Apple is ever more a closed hardware architecture with few options. If you want choices, Apple is not for you.
There are no configurations even close to running something comparable to frontier model variants, they're simply far too large, but something like full precision Qwen 35b or DeepSeek 70b at 50+ t/s is well within available configuration, and potential for plenty of room for large context sizes.
1.2TB/s memory bandwidth unlocks a lot with 256GB unified, and agentic AI is pretty good at optimising performance.
For comparison, to get 256GB with NVIDIA, you’re looking at a DIY workstation build (need pcie lanes), and like $70k?
The spark’s ~250gb/s bandwidth doesn’t really count here.
I don't actually own a car and my startup is bootstrapped and our salaries are modest. But the one thing we spend on is laptops. I have M4 max pro with 48GB. That thing was on the expensive side (~4.5Kish). But it delivers a lot of value and I spend most hours I'm awake using it. I like fast builds. I like that I can try out open source AI models. And I like just having the option to run those.
We actually lease them and mine costs something like 105 euro/month. Including Apple Care. I don't need a Mac Studio but I could see some roles where that would not be a crazy expense. Even the tricked out version that basically only costs the same as a very modest car.
They're eating nvidia's lunch.
Compared to something like VRAM it's slow.
We no longer need CD/DVD/floppy drives, storage has shrunk/moved to the cloud. The only thing that's really grown inside a pc case is the video card, and most of these ITX cases are built specifically around fitting popular cards.
Even folks primarily focused on gaming are probably thinking that a full ATX case is a lot of wasted space.
Maybe it's just me, but I think ATX full and mid towers are going the way of the dinosaur.
Seems like miscalculation. If they had their own fab for RAM, they could completely corner the market today.
But +4000$ for an additional 128GB of ram is simply milking the customers, as they know they will have many of them.
Plus introducing features like RDMA over thunderbolt, which is critical for distributed inference/training/etc. On the software side, Apple is investing heaps.
It's still ridiculous they don't support expandable NVMes, but the memory being soldered makes sense, you need it for 1.2TB/s bandwidth.
They are still selling high-margin hardware. Apple loves selling high-margin hardware.
I want a computer dammit, not an appliance.
Never ended up happening. I didn't get much done at home at all and what I did get done was mostly on the couch; not a great environment for serious work. (I have an office where I do for-profit work so it's not an issue, but still, I like my side projects too)
Eventually I had enough decommissioned computer parts that I could assemble them and re-commission them into a working desktop. So I now have a desktop again. And I actually end up sitting at the desk working on stuff on the desktop in a way I rarely did with the laptop.
https://support.apple.com/en-my/guide/remote-desktop/apdf8e0...
Staggering?? I can count on no hands the number of times that a fact or figure has caused me to stagger.
But, that doesn't make it a good deal. It just means the Apple tax doesn't apply when stacked up against AI machines and with memory prices being so out of whack. I'm still planning to wait until the RAMpocalypse ends before I buy any more hardware.
Computers are never "future proof".
A NVIDIA RTX 6000, 96 GB at 1.7 TB/s, is 13 grand.
This 256 GB at 1.2 TB/s Mac is extremely competitive, it will be sold out everywhere.
I actually wouldn't want a serious model shipping 'on disk'. Models release so often, it's going to get outdated quickly. LMStudio is trivial to set up.
Basically, Apple gets to cheat because they shove everyone onto the same IC & make the OS that runs on this SOC.
> A fully configured IBM Personal Computer AT (Model 5170) with expanded memory and storage cost around $5,795 to $6,000 at its launch in August 1984, which equals roughly $18,600 to $19,300 in 2026 USD.
It would be significantly cheaper to fly to a tariff-free country and buy there.
I can tailscale into my home network, but what next? VNC/TeamViewer/Remote Desktop setups are all mediocre imho.
Screen is small and is only one. Ergonomics is entirely messed up. Either your screen is too low, or your keyboard is too high. Keyboards are non-ergonomic and have to be made with compromises due to height limits. Touchpad instead of mouse/trackball is compromise for many - and also stuck at one position.
And yet they have somehow spread despite number of people going on business trips not really increasing.
And that, from mental load standpoint, is not healthy for most folks.
I'm using Flash heavily, and I would describe it as nearly as intelligent as Sonnet-class in agentic coding, but more usable. Less world knowledge of course, and definitely a bit less intelligent; but not _that_ much.
On usability: Takes less handholding, less likely to make unsolicited refactors or whatever, and the writing style is readable.
It's not great at super-long-horizon goals as the Claude 5 models are; but if you have a good harness, you can get around that.
1-2$ / hour.
I'm not regretting my setup at home as it got paid by my company which makes sense here, but paying for electricity is quite high and makes already 0.3$/hour alone.
I would argue, the most interesting use case for running it at home is some personal agent which you want to run 24/7.
I bought a Macbook Air in the interm waiting to see what the Macbook Ultra looks like, but honestly—it's the best form factor ever. I love it! Even though it's only like a pound heavier, the Pro feels like a monster.
Thinking about getting a Mini or Studio with more horsepower to stay at home.
Any other apps or suggestions? I'm still not exactly sure what working this way looks like.
Only reason to buy this if you want to own your compute.
Experimentation and inference are all going to be cheaper on the cloud
A 8 years old graphics card can still play modern games. Ten years ago playing a modern game on hardware that old would've been unthinkable.
And with how the market is right now, we'll be stuck on the current "reference level" of hardware for a while longer.
It was future proof but not really because it struggled a lot in its final years.
i'm still using an old i7 3770k @ 4.8ghz with 16gb (ddr3) ram running linux for random tasks like executing tests. obviously, power consumption is higher.
my main machine is a MBP M1 Max which i use for everything. i also have my main linux desktop workstation that has a 5950x with 128gb (ddr4) ram.
i'll probably get 2-5 years out of my MBP, and my AMD workstation will probably be good for another 5-10 years.
i'm not a gamer, but i have a 3080. i'm sure my 5950x will still be good for gaming in 10 years if paired with a modern GPU.
Upgradeable components however could go a loooong stretch towards that goal. It can't be that hard to follow a common form factor for at least the housing across two or three generations to allow a reuse of everything but the main PCB.
Tend to be better than Apple AI.
Another example as a developer, one particular large project took an hour to build on a spinning disk, on a SSD it takes 2mins
So, yeah, it's really noticable improvement
So while have having this massive almost-symmetric fibre pipe is cool on paper, I haven't felt a huge need to install 2.5G gear all over the house.
Unfortunately, it relied on Display PostScript and Quartz née Display PDF isn't architected to allow that sort of remote display/access on a per application level.
It worked relatively well, but wasn't perfect. It was as close to what you're describing as I've seen, though. This was a few years ago; something like this might work even better now.
The comparison should be against renting in the cloud for the duration of your task for training and research or using pay-per-api-call providers for general inference instead of buying your own hardware (and paying the electricity and cooling bills on top), because let’s face it, the models you want to use are probably the same ones available on inference providers (but, yes, some are more trustworthy than others).
Speaking as someone that does ML/AI research, you are essentially paying a huge premium for being able to just run your Python script at any time without setting up a deployment script and harness to run the job remotely, while your hardware sits essentially idle the rest of the time.
The only way to make the math work is if you rent your hardware in the background for inference while you’re not using it in anger, but despite all the startups and promises that has never become as streamlined as mining bitcoins or shitcoins used to be and they don’t pay out as much as they say they would. Renting your hardware for training is another option but doing that is a lot more involved, options are fewer and farther in between, you won’t get as much utilization out of it, and doesn’t let you feasibly abort running tasks at a moment’s notice.
data processing, LLMs, model loading, MoE loading, etc, etc relies on very fast storage to keep your GPU saturated.
256GB model is $10k and the 512GB version will probably be double
My ideal Mac Studio would have an NVMe slot or two for additional internal storage, and those slots could be accessed without opening the case. But Apple won't do that, as convenient internal storage upgrades would likely lower their profits.
The maths to me was basically equivalent to prepaying for 242 days of runpod pricing for the same GPU; and I reckon I'd be able to get 6+ years of use out of this card with 96GB.
Plus there's the resell value -- it's actually appreciated by ~50% since I bought it.
Plus I do really enjoy that it's 100% local. I wouldn't feel comfortable giving my agents this much information if inference wasn't 100% local.
I wouldn't get another one, I wouldn't have as much value, but one is definitely paying off for me on the financial side.
Extremely high bandwidth is great for copying data, but not as relevant for walking chains of pointers, where latency/cache/TLB entries are more important.
So just saying "high bandwidth == better" is true when other variables are the same, but they rarely are, especially in comparison to x86-64 offerings.
All of these are independent that it is a SoC with on-package DRAM.
I expect it to stay a mediocre gaming PC for the next 3 years maybe 5 years.
16GB RAM RTX 3060 TI (8 GB VRAM)
Good for inference; however if you like to train, data format support and effective performance is limited (M5 Pro). Some hardware features are not exposed or extremely slow.
You’ll be fine for inference, but pales in comparison to what a RTX 6000 Pro can do for compute/matmuls/training.
Otherwise you'll have to wait to see if the AI circular financing club collapses- if you still have a job, there should be deals to be had...
But for the mac pro, they would say something very obscure.
"100-120V AC or 200-240V AC (wide-range power supply input voltage)" and the maximum current is "12A (low-voltage range) or 6A (high-voltage range)".
They're trying NOT to say it had a 1440 watt power supply.
opens in new window
PRESS RELEASE August 25, 2026
CUPERTINO, CALIFORNIA Apple today announced the new Mac Studio, featuring M5 Max and the all-new M5 Ultra, delivering a monumental leap in AI performance and even faster graphics for the most demanding pro workflows, all in its signature compact design that lives right on a user’s desk. Now featuring up to 4.3x faster AI performance,1 up to 2x faster storage,2 up to 1.8x faster graphics,1 and up to 1.3x faster CPU speed,1 along with higher memory bandwidth, Mac Studio empowers creatives, developers, AI researchers, data scientists, and more to push the boundaries of what they can do. Mac Studio with M5 Max features an 18-core CPU, an up-to-40-core GPU with Neural Accelerators built into each core, and up to 128GB of unified memory, accelerating complex pro and AI workloads. With the powerful M5 Ultra, Mac Studio scales up to a 36-core CPU, up to an 80-core GPU, and a staggering 512GB of unified memory, enabling users to run enormous LLMs entirely on device. Wi-Fi 7 and Bluetooth 6 come to Mac Studio for the first time, while Thunderbolt 5 rounds out its extensive connectivity, so users can take advantage of blazing-fast external storage, PCIe expansion chassis, and powerful hub solutions for the most intense workloads. Thunderbolt 5 also enables multiple Mac Studio systems to be clustered, bringing up to 3x faster performance for distributed AI inference when compared to a single system.1 Together with Studio Display and Studio Display XDR, along with the power of macOS 27 and the next generation of Apple Intelligence,3 including Siri AI,4 it is the ultimate pro desktop. The new Mac Studio is available for pre-order starting today, with availability beginning September 22.
Mac Studio is also a powerful platform for the rich ecosystem of tools AI researchers and developers rely on every day, utilizing the advanced frameworks in macOS. Core AI is a brand-new framework for building, running, and deploying AI models on Apple silicon. It provides an architecture optimized for Apple silicon, including unified memory, CPU, GPU, and Neural Engine, allowing developers to deploy full-scale LLMs locally and bring their own custom models into their apps. MLX, Apple’s open-source machine learning framework optimized for Apple silicon, enables developers to run, train, and fine-tune models with exceptional efficiency on Mac. In addition to these powerful frameworks, combined with Xcode and a robust ecosystem of AI tools and solutions, Mac Studio provides a complete, end-to-end platform for AI development — from experimentation and training to deployment.
Built for users who demand powerful performance in a compact footprint, Mac Studio with M5 Max is ideal for musicians, photographers, software engineers, and designers pushing real-time 3D and motion graphics. Mac Studio with M5 Max delivers a huge boost in performance, featuring an 18-core CPU with 6 super cores and 12 performance cores, so developers can compile code even faster. The up-to-40-core GPU with Neural Accelerators is now up to 50 percent faster than the previous generation, boosting graphics-intensive tasks like game development with higher frame rates and more complex scene geometry.1 With up to 614GB/s of unified memory bandwidth, M5 Max delivers superfast on-device AI compute, enabling users to run LLMs, generate images and video, as well as accelerate complex workflows.
The new Mac Studio also includes third-generation hardware-accelerated ray tracing, delivering faster, more realistic lighting, reflections, and shadows across professional 3D, VFX, and design workflows. Enhanced shader cores boost parallel processing, enabling smoother real-time viewport navigation and faster offline renders in creative workloads. In addition, its powerful Media Engine supports hardware-accelerated H.264, HEVC, ProRes, and AV1 decode, allowing filmmakers to color-grade uncompressed 8K footage and process multiple concurrent video streams with ease.
Up to 10.7x faster LLM prompt processing in LM Studio when compared to Mac Studio with M1 Max, and 3.9x faster than M4 Max.
Up to 7.4x faster text-to-image performance when compared to Mac Studio with M1 Max, and up to 3.5x faster than M4 Max.
Up to 5.3x faster Magic Mask performance in Blackmagic Design DaVinci Resolve Studio when compared to Mac Studio with M1 Max, and up to 3x faster than M4 Max.
Up to 3.5x faster basecalling for DNA sequencing in Oxford Nanopore MinKNOW when compared to Mac Studio with M1 Max, and up to 1.9x faster than M4 Max.
Engineered for professionals who tackle the most extreme workloads, Mac Studio is the ultimate pro desktop, taking performance to an entirely new level. There is no other chip like M5 Ultra, which delivers the highest levels of performance and massive amounts of unified memory, enabling pros to push the limits of what they can accomplish on a single machine. Filmmakers can color-grade uncompressed 8K footage in real time, VFX artists can render complex simulations, and data scientists can train local AI models on expansive datasets. The new Mac Studio with M5 Ultra features an up-to-36-core CPU with 12 super cores and 24 performance cores, delivering up to 1.3x higher multithreaded performance than M3 Ultra.1 Its up-to-80-core GPU, the most powerful Apple silicon GPU ever, brings Neural Accelerators to the Ultra chip for the first time, enabling up to 4.3x the peak AI compute performance when compared to M3 Ultra.1 It also features up to 1.8x faster graphics than the prior generation, providing smoother real-time 3D rendering for VFX workflows.1
Mac Studio with M5 Ultra shows an Adobe Premiere screen featuring an athlete running in the rain.
Up to 15.4x faster CopyCat ML training performance in Foundry Nuke when compared to Mac Studio with M1 Ultra, and up to 3.3x faster than M3 Ultra.
Up to 9.8x faster LLM prompt processing in LM Studio when compared to Mac Studio with M1 Ultra, and up to 4x faster than M3 Ultra.
Up to 8.2x faster text-to-image performance when compared to Mac Studio with M1 Ultra, and up to 4.3x faster than M3 Ultra.
Up to 4.7x faster scene rendering performance in Maxon Redshift when compared to Mac Studio with M1 Ultra, and up to 1.7x faster than M3 Ultra.
The new Mac Studio also features faster storage and a comprehensive array of pro connectivity. Storage performance is up to twice as fast, with a next-generation SSD architecture, delivering industry-leading read and write speeds for rapid project loading, file transfers, and loading huge LLMs.2 Thunderbolt 5 ports deliver transfer speeds up to 120Gb/s of bandwidth, so pros can connect high-performance peripherals, displays, PCIe expansion chassis, and external storage to utilize its remarkable speeds. The Apple-designed N1 chip brings Wi-Fi 7 and Bluetooth 6 to Mac Studio for the first time, delivering improved performance and reliability to wireless connections. Mac Studio now enables genlock over USB-C for precise synchronization between a display and professional camera capture like iPhone 17 Pro. It also supports up to eight displays, or up to four Studio Display XDR at full 5K resolution and 120Hz, providing an expansive screen for the most demanding projects.
Customers can pre-order the new Mac Studio with M5 Max and M5 Ultra starting today, August 25, on apple.com/store and in the Apple Store app in 30 countries and regions, including the U.S. It will begin arriving to customers, and in Apple Store locations and Apple Authorized Resellers, starting September 22. Mac Studio with 512GB of unified memory is coming in late October.
Mac Studio with M5 Max starts at $2,499 (U.S.) and $2,299 (U.S.) for education. Additional configure-to-order options are available at apple.com/mac-studio.
Mac Studio with M5 Ultra starts at $5,499 (U.S.) and $5,099 (U.S.) for education. Additional configure-to-order options are available at apple.com/mac-studio.
With Apple Upgrade, eligible customers in the U.S. can lease a new Mac with low monthly payments and easily upgrade at the end of their lease: apple.com/shop/apple-upgrade.7 Lease Mac Studio with M5 Max with Apple Upgrade from $48.99 (U.S.) per month (excluding taxes and any trade-in credit) for a 36-month lease. Lease Mac Studio with M5 Ultra with Apple Upgrade from $110.10 (U.S.) per month (excluding taxes and any trade-in credit) for a 36-month lease. Additional configure-to-order options are available at apple.com/mac-studio.^
Additional technical specifications, configure-to-order options, and information on Studio Display, Studio Display XDR, and Magic accessories are available at apple.com/mac.
macOS 27 is available for testing in public beta through the Apple Beta Software Program at beta.apple.com, with availability as a free software update this fall. For more information, visit apple.com/macos. Features are subject to change. Some features may not be available in all regions or in all languages.
With Apple Trade In, customers can trade in their current computer and get credit toward a new Mac. Customers can visit apple.com/shop/trade-in to see what their device is worth. Customers in the U.S. who shop at Apple using Apple Card can pay monthly at 0 percent APR when they choose to check out with Apple Card Monthly Installments,8 and they’ll get 3 percent Daily Cash back — all up front.9 More information — including details on eligibility, exclusions, and Apple Card terms — is available at apple.com/apple-card/monthly-installments.
AppleCare delivers exceptional service and support, with flexible options for Apple users. Customers can choose AppleCare+ to cover their new Mac, or, in available markets, AppleCare One to protect multiple products in one simple plan. Both plans include coverage for accidents like drops and spills, battery replacement service, and priority support from Apple Experts. For more information, visit apple.com/applecare.
Every customer who buys directly from Apple gets access to Personal Setup. In these guided online sessions, a Specialist can walk them through setup or focus on features that will help them make the most of their new device. Customers can also learn more about getting started and going further with their new device with a Today at Apple session at their nearest Apple Store.
Text of this article
Media in this article
Testing was conducted by Apple in July 2026. See apple.com/mac-studio for more information.
Results are compared to previous-generation Mac Studio systems with Apple M3 Ultra, 32-core CPU, 80-core GPU, 512GB of unified memory, and 8TB SSD.
Apple Intelligence features are currently available for testing through the Apple Beta Software Program, and will be available with macOS 27 this fall for users with an Apple Intelligence-enabled device set to a supported language. Apple Intelligence is available with support for these languages: English, Danish, Dutch, French, German, Italian, Norwegian, Portuguese, Spanish, Swedish, Turkish, Vietnamese, Chinese (simplified), Chinese (traditional), Japanese, and Korean. Some features may not be available in all regions or languages. For feature and language availability and system requirements, see apple.com/apple-intelligence.
Siri AI is currently available for testing through the Apple Beta Software Program. Siri AI will be available with macOS 27 as a beta later this year for users with a supported device set to English, and Apple will quickly expand support for more languages.
Product recycled or renewable content is the mass of certified recycled material relative to the overall mass of the device, not including packaging or in-box accessories.
Breakdown of U.S. retail packaging by weight. Adhesives, inks, and coatings are excluded from calculations of plastic content and packaging weight.
Apple Upgrade is a device leasing program available in the U.S. (excluding U.S. territories). Leases are provided by Klarna; subject to eligibility and credit approval, including final approval at checkout. To be eligible, you must be a U.S. resident, at least 18 years old (or the legal age in your state), have an accepted credit or debit card, and have an Apple ID. Additional eligibility criteria apply. Device must be in good condition upon return; damage fees may apply. For iPhone only: In order to lease an iPhone, you must select an eligible carrier (but you cannot use a prepaid carrier plan). Upgrades require entering into a new lease and are subject to eligibility and credit approval. Apple Upgrade is not available on refurbished devices or online at the following special stores: Apple Employee Purchase Plan; participating corporate Employee Purchase Programs; Apple at Work for small businesses or enterprises; Government, Education, or Veterans and Military Purchase Programs.
Apple Card Monthly Installments (ACMI) is a 0 percent APR payment option that is only available if users select it at checkout in the U.S. for eligible products purchased at Apple and is subject to credit approval and credit limit. See support.apple.com/en-us/102730 for more information about eligible products. Additional limits and restrictions apply. See the Apple Card Customer Agreement for more information about ACMI.
Apple Card is subject to credit approval, available only for qualifying applicants in the United States, and issued by Goldman Sachs Bank USA, Salt Lake City Branch.
^ This offer is for a consumer lease, not a purchase or loan. Lease provided by Klarna Inc. for 24- or 36-month term. Your first monthly payment is due approximately 30 days after device is shipped or available for pickup. Lease approval is subject to eligibility and is based on creditworthiness. Monthly payments are based on the selected device and lease term.
For example: For Mac Studio with a purchase price of $2,499 (excluding taxes and any trade-in credit), the typical monthly payment is $48.99 (excluding taxes and any trade-in credit) for a 36-month lease term and $67.99 (excluding taxes and any trade-in credit) for a 24-month lease term.
No security deposit required. A trade-in device may reduce monthly payments. Advertised monthly payment amount may not include a trade-in device’s estimated value. Upgrades are not guaranteed and are subject to eligibility and approval.
Terminating your Apple Upgrade lease: Closing your lease and returning your device terminates your lease. You may incur a substantial charge up to the amount of your remaining lease payments if you terminate your lease before the end of your initial lease term. You may have the option to upgrade to a new device by entering into a new lease agreement and returning your prior device. If you upgrade, your new monthly payments may be greater than your prior monthly payments. If you do not upgrade, terminate your lease, or purchase your device by the end of the initial lease term, the lease will convert to a month-to-month lease for up to six months. Your monthly payments may increase during the month-to-month period. If you take no action at the end of your extension period, you will be charged for the amount due to exercise the purchase option under your lease. You will not own your device at the end of your lease, unless you pay the amount due to exercise the purchase option. Insurance is not included in your lease, and you may incur damage fees if the device is lost, stolen, or not returned in the condition required by the lease.
Apple Upgrade lease eligibility: Leases are only available to U.S. residents (excluding residents of U.S. territories). Leased devices are only available for shipping to U.S. addresses (excluding U.S. territories) or pick up at Apple Retail stores in the U.S. (excluding U.S. territories). To be eligible for a lease, you must be at least 18 years old (or the legal age in your state of residence), have a valid social security number or individual taxpayer identification number (ITIN), have an accepted credit or debit card, have an Apple Account in good standing, have a Klarna Account, and be able to receive security verification codes via text message. Leases are not available on refurbished accessories or online at the following special stores: Apple Employee Purchase Plan; participating corporate Employee Purchase Programs; Apple at Work for small businesses or enterprises; Government, Education, or Veterans and Military Purchase Programs.
I have a bit of paranoia/anxiety about AI, but it's not what most people are concerned with. I understand the limits of these tools very well, and still find them extremely useful. What concerns me is that it's going to become difficult to impossible in the future to run local models which have near-SOTA capabilities in a way in which you can exercise full control of the model. I see the writing on the wall, and its more than worth it for me to invest early to ensure my own capabilities. I am very much not a fan of our "you'll own nothing and be happy" directionality for the world, and I am (at least currently) privileged to have the means to slow that decline for my own self.
Would be nice if someone knowledgeable about electrical engineering and manufacturing processes could lay out some valid reasons for manufacturers to integrate RAM onto the motherboard.
- 120v input plug
- not rack-mounted
- has a video out port
EDIT: AMD too, it's not limited to Nvidia, nice.
Its update policy can result in this sort of regressions in a middle of a release. One thing that's nicer thing about macOS is that a released version doesn't regress as much (even if they are buggier at release; but in that case you can just wait until a later point release to upgrade).
It's not like you have to be on a plane for the portability to be useful.
But the couch is just so comfy.
It feels like PCIe is a bit of a boat anchor here. There's a SATA->NVMe style transition waiting in the wings to make this all so much better. We really need post-PCIe GPUs. CXL with it's very small low latency flits. This is an "almost certainly not" but I wonder if you could mix PCIe and CXL so you could have the GPU memory expose vmeme as a bunch of CXL.mem pools but still have an otherwise pretty normal GPU. It seems madness that UALink went all in on GPU-to-GPU with no affordances for connecting to host computers.
Efficiency is improving, both in hardware and in software and in intelligence density (smaller models can effectively do more of the AI work that needs doing), so I think the pure data center plays will falter. If there isn't some other business attached, they're never going to recoup their investment. Anthropic and OpenAI are buying all the compute they can find right now, but efficiency gains, especially those coming out of Chinese labs where they must be more efficient to compete, will make it less and less of a problem.
I mean, think about the hardware we use for AI. It's basically an accident. GPUs were not designed for AI (though they are becoming more focused on AI). The specialized AI hardware industry is just ramping up.
So, we're still early in the curve for how efficient both the hardware and software can be at performing these tasks, and given the effectiveness of recent very small models (e.g. DeepSeek V4 Flash 0731 and Qwen 3.8 27B), I just don't see a long future for giant data centers built around billions of dollars worth of last years graphics cards. As with the crypto mining operations, at some point, it becomes more expensive to run the hardware than it makes in revenue. And, as with the crypto mining operations, when the money dries up, the hardware hits eBay and prices drop.
What is changing is that there genuine demand for more capabilities disproportionate to the cost decrease curve. Fab demand and supply constraints have slowed or even reversed some cost decreases - but that is still getting absorbed by the overall systems costs when you are looking at things like laptops. If you all you want is the last decades demand to browse the web and use office - things are cheaper than ever.
If you haven't tried Screen Sharing since they deprecated VNC and switched to their proprietary H.264-based protocol, its worth trying. Even YouTube videos play just fine with no noticeable lag.
If your computing needs line up, it's a very serviceable approach.
A laptop is a distinct tool from a desktop and if you try to use it like a desktop, I agree it is a terrible substitute. Personally I find laptops vastly more ergonomic than a desktop, but I never program with my feet on the ground.
iMacs are great for a lot of use cases, but my image of the typical HN user would prefer to keep the monitor separate.
There is some consolation there
I can run agents using deepseek v4 flash or Qwen 3.8 on my m3 ultra and it will be lukewarm and the fan will eventually start blowing softly.
Care to guess the approximate price of the MBP I bought earlier this year?
Not that many of us, actually. Only Montana, New Hampshire, Oregon, and some parts of Delaware and Alaska have no sales tax. https://commons.wikimedia.org/wiki/File:Sales_tax_by_county....
I haven't added my iPad to the Tailnet yet but i reckon that it could become a very comfortable and productive device for me.
Macs are totally “fine” for light server duty… as is just about any computer of the last decade+. The CPUs are beasts, the disks are screaming fast.
The operating system itself may not be ideal at serving but you can just run Docker/Orbstack if you need to do something especially Linux-y.
I’d put the question back on you — what are scenarios where an Apple Silicon Mac wouldn’t cut it as a light server for one person or a handful of people? About the only scenario that comes to mind is scenarios where you expect to utilize it so heavily that the fans are running for many hours a day. At some point those are either gonna wear out or just ingest so much dust that the machine runs hotter and needs a deep clean. But even that is largely mitigated by just pointing an external fan at it.
At that point just rent proper GPUs in the cloud, you'd have way more power and pay only what you use for.
Last year when I was browsing the only recentish Apple silicon capable of driving that was the M3 Ultra.
I've found my smartphone's the best device for that. I wrote an entire programming language using my phone.
Been trying to make a handheld cyberdeck to replace the phone with something better, but it's still a long way from being real.
If you can show me a model for which a Mac is faster than the RTX 6000 then I’ll be happy to update or retract my statement.
Yes, the Mac might get lukewarm, but it will take 2-3+ times longer to do the same task.
Are you using Apple displays or did they fix it?
This new Studio? Can't find a config under $5k I'd bother with. But for the MBPs that number still mostly tracks for the average Pro user. (I buy large and run it into the ground so long I mistake the ground for the computer's remains.)
If you just want to run Qwen 3.8 27B and Deepseek v4 Flash in perpetuity and that's it, there are a lot of solutions that will work and this is a fairly user friendly one.
Years ago I realized running a 100W PC all the time was REALLY expensive, so I switched to an old linux laptop at 30W (about $4/month). That helped, but I moved to the m1 mac specifically for the power efficiency. It does all the things my linux server did, and it does them at 6W (75¢/month).
I've found no competitor with similar performance that can run in such a low power footprint. M4 mini's are way better at power/performance, and I imagine their price is about to come way down since the M6 mini just got announced.
Software-wise, it's different, but mostly equivalent. Homebrew or macports has a similar software inventory to debian. And Apple's container framework is a welcome improvement over colima for running most container workloads.
There's just less space, so it's harder to get things in and out. And you have a smaller cooler because there's less space, at least for air cooling.
I haven't used itx with video cards, but that's hugely constrained...
So not as flexible as apple's unified memory.
Well it might be an idea to keep the layout of the mainboard and connectors the same.
That way, instead of having to upgrade the whole machine, all it would need is a new mainboard. Framework for example managed to pull that off, and in mobile at that, where constraints are much worse than for a desktop computer.
Are your referring to Taalas / chatjimmy ?
I definitely think we'll see an ASIC-like approach in the future, especially for embedded small models where it may require minimal silicon area and can result in near-realtime performance. But at the frontier, I don't think this is a solved problem and will continue to have model weight churn that will advantage more flexible general-purpose hardware.
My still-being-used 2012 MBP (which cost me about $3K) says, “hi”.
And, as you point out, the new computers I want blow Dvorak’s hypothesis out of the water. Never would I have guessed 30 years ago that Dvorak would be wrong the other direction on price.
It’s pretty good.
To be clear, it’s not ever supposed to be a primary. It just becomes one from time to time when I make it full screen and am not paying attention.
It's not the same thing though. On the M-series, CPU and GPU share a unified memory architecture and ram is much more tightly coupled to get it to go faster. A closer example would be the Framework desktop, actually, where memory is also soldered in for the same reason.
¹ drivers are responsible to get the car into a low earth orbit themselves and need to be familiar with the orbital maneuvers needed to accelerate the car to 900mph
It’s a very non-Apple thing to do, but it’d be pretty awesome if they did.
