A lot of those "up to"s are expressing user options, though -- "up to" 512 GB RAM means that there are configurations that include that, but also cheaper configurations that don't. That's a pretty different beast than "up to 4.3x faster performance", which means (presumably) that exactly one benchmark showed a 4.3x improvement and the rest showed less -- which is to say, means very little.
It would also be incorrect. "Up to" doesn't mean any possible upper bound, it describes the top of a known range. I can't say a car I'm selling goes "up to" 900mph if it tops out at 120mph.
Due to pricing insanity (not that Apple prices weren’t insane before the ram/ssd shortages) I’m not in the market but I do wonder if my next computer should be a Mac Studio instead of a MBP that lives its life docked. Might be better to just run a Studio and Neo for the very few times I actually need remote capabilities.
I used to have a high-powered laptop, but just use a combination of ssh and NFS to my machine at home from a low powered laptop for travel these days. It works well.
Makes managing both backups and handling failure scenarios involving loss or unauthorised access to the laptop less of a hassle as well.
I've been thinking about this a fair bit recently.
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.
There is a definite mental aspect for most WFH folks to having a space that is dedicated to work. I'm not unique in saying this, but the way I put it is "If you work from anywhere in your house, then you're always at work."
And that, from mental load standpoint, is not healthy for most folks.
I've done that, but I chose a Framework Desktop instead. The latest Fedora is closer to Snow Leopard than anything Apple has to offer. Downside is that I still have my MBP because of the lock-in and occasionally pick it up to do computer stuff in weird places.
I got used to the hub-and-spoke model at home (previously thin terminal, server-client, etc.). Big ole desktop/server and smaller devices that (ab)use it remotely. Roam around with a smaller computer/tablet/phone. Tailscale to bind it all together.
If your computing needs line up, it's a very serviceable approach.
To me the idea of working on (non-docked) laptop always seemed like an idea that you would do only if there is no other possible way.
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.
I would not use Neo, Air with 24 GB ram should be your minimum because you will want to do some work locally even when you're running a VPN/SSH thin client setup.
I'm currently SSH-ing into my workstation from my M4 Air with 24 gb ram and it's ideal for this flow. Slack/editors/clients/browsers/etc. easily gobble up over 16 GB. I have no more dev tools/compilers/source on my client machines, everything is dockered up on remote workstation in isolated VMs (too much supply-chaining).
My only downside to using a pro is not having 120/4k HDMI port on air and my dock won't support it with Apple (it does with windows)
Another option is a 'maxed out' mini e.g M5 Pro/64GB. Mini is super easy to travel with if you know there'll be a 'dock' at the far end e.g office<>home or whatever.
So I can somewhat speak to this, as I actually did this for a while c. 2021 and 2022.
The issue (apart from Mac mini still having the old, bigger form factor back then) is that this requires a full shutdown (obviously), and that is more friction than opening a closed laptop lid. It just takes a moment for every app and background service etc. to settle back in after, and depending on how your brain works, you might not like that a whole lot.
It absolutely is a cool feeling to carry a pretty mighty desktop in the backpack, though.
I think it's actually good to have a forced reboot from time to time, but then I'm not very disciplined in closing stuff I'm no-longer using! Especially like docker containers I was using months ago, that I forgot to shutdown.
Having replaced my MacBook with a Mac Mini, I would reconsider. The MacBook is just such a _complete_ package. Great speakers, great keyboard, fantastic screen, the fingerprint sensor thingy.. Takes a lot of gear to match that
I thought the question was low-end MacBook + mini vs high-end MacBook. The low-end one has all those nice things. I wouldn't sacrifice that. If it has to be MacBook + super old used mini as home server, so be it.
I’ve had iMacs for almost 20 years. My last one was indeed my last. Without target display mode (use the Mac as a monitor), I’m ditching a perfectly good monitor. I was going to buy a Mac Studio and a good monitor to replace the iMac until the spouse reminded me that we are now retired and will spend time in a camper. So a MBP for me (and BenQ’s Mac-specific monitor), but others might do well to consider a Mac Mini/Studio.
iMacs are great for a lot of use cases, but my image of the typical HN user would prefer to keep the monitor separate.
My M1 Pro drives 4 screens no problem. The trick is that you can only attach two through one Thunderbolt port, so you have to attach the 3rd one via the other port instead of your dock. (The 4th screen is the laptop's built in screen)
Honestly the screens become more of a liability than an asset to me past 2 (including the laptop screen). I've tried. Even if I'm knee deep in work and have like 4 servers I'm monitoring, my eyes are only going to look at one screen at a time.
My goto. Even ignoring speed, it's nice to have a remote machine that keeps doing whatever it's doing while your laptop is closed. And the ARM Macs idle at such low power that it's not wasteful like my MacPro4,1 was haha. My UPS's ammeter doesn't even display the Mac mini's draw.
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.
I had the same thought, I grabbed a studio two years ago for this reason and it’s been great. 99% of the time lack of portability isn’t a concern. Every now and then (e.g. travel) I notice the limitation, but it’s not much of an inconvenience to just not do some work for a bit.
Plus remote work is getting easier and easier. There are so few instances when I'm not able to get online. If we lived in a world where hardware were getting cheaper, it might make sense to splurge. In this environment I think the Neo is perfect.
Build quality of the Neo is extremely good, I love the keyboard — it’s more tactile and reminds me of early 2010s MacBooks.
I’ll be selling my M4 MBA soon, I genuinely use the Neo more. Huge difference in typing experience.
Great repairability is a plus. It was super easy, and actually fun to open. Felt like unboxing an Apple product. Applied the thermal paste mod for $10 which works excellently; I’ve had it shortly after launch.
And I love the notchless display, even if I wished the color gamut was a bit better.
I dusted of my lightest computer with an M1 chip and use Tailscale to make my network virtual from anywhere. Been running a. Pi5 as a main house hub and an M1 Pro as an always on Mac. It would be nice to go all out and make a Studio a hub I can just screen share into for major compute.
>I do wonder if my next computer should be a Mac Studio instead of a MBP that lives its life docked.
Having owned 3 MacBook Pros since 2008, the decision to make my next computer be a Mac Studio came down to (1) MacBook thermal throttling that slows down CPUs when it starts to overheat and (2) easier upgrade of Mac Studio SSD with after-market storage module whereas the MacBook requires more complicated disassembly and hot air gun to dislodge the surface mounted SSDs.
I have a brand new M5 Pro MacBook Pro I don't like it when the fans turn on. The Mac Studio will be faster and quieter for the same workloads.
Sorry for not being clearer. I don't like the MacBook's noise when the fans turn on.
The Mac Studio has bigger heat sinks to delay the need for thermal management -- and if its fan does need to turn on, the bigger size means it's still silent instead of the high-pitched whooshing noise the tiny fans make in the MacBook.
At my current job, one of my biggest blunders was thinking "Let me just order the same hardware as most of my teammates to avoid unnecessary complications".
Most, if not all, of our current work happens on remote cloud vms. Now I'm stuck with carrying a 3KG monstrosity to work.Every day.
Absolutely no positives compared to my ThinkPad that weighed less than half in my previous job.
Remote development is "good enough" these days. With VS Code, Development containers etc... Having a light weight, portable laptop is so much nicer than a laptop that you can't even rest on your lap for long duration.
The only thing you need to be mindful of using light weight laptops is not having enough RAM to fit all your browser tabs..
I totally agree I use containers through propelcode.app which means I can code on any device including my phone and the environment is the same as the server target. It’s even more important with agents that can delete files and change OS settings. I never need to worry that a coding session ends up breaking my main OS environment by deleting or changing a file.
Yeah I stepped down to a smaller MBP. the only reason I didn't go for an air is my home setup with dual monitors involves using the HDMI port. There probably is a dock or something out there though.
Everything is a container or VM now, and none of it runs locally for me.
I have a desktop (older intel) with giant monitors and a keyboard for when I sit at the desk. I have the laptop for when I travel, go out or just want to work from the couch.
When I do my next upgrade to "better hardware" I'm not migrating a machine, rather I'm migrating the containers. My workflow is such that if I loose one of the boxes I sit at to a cup of coffee I really wont care other than the financial loss of a new laptop or keyboard.
The biggest win in all this was dumping the off the shelf firewall/router and moving to Opnsense. Wireguard vpn lets me route all my traffic through home for all my devices (and what is now a growing home lab).
There are scopes of work that this setup would not work for. I would not want to be a video editor with this set up, it's not ideal if you want to play AAA games. But for what I do, it is pretty ideal.
I had the same view recently. For the past year I’ve been using my iPad to remote into both my MacBook Pro M1 Max and my racked Linux workstation at home using Jump and moonlight/sunshine, respectively. Never looked back
I've been holding out, because I think my next purchase will be a Studio with an Ultra Chip in it. I'm wanting it to be a "forever" server, so I'm holding out while I can.
Supply rumours are next year we see an M7 AI-focused chip with large inference performance upgrades. It's unlikely we'll see heavy upgrades in other areas. If you care about AI, it's worth waiting. If you don't, pull the trigger now. RAM constraints are likely to get worse next year. Or wait 2-3 years and prices should be back to Earth (plus newer and even better chips).
Yeah, but how many years until 128GB+ is attainable by mere mortals again? My 2021 home server build was 64GB of RAM. My 2025 build was 32GB and zram. :/
I just wait for a cycle or two where the leaps and bounds are more like hops and steps. So if the M7 Ultra improves inference by 2x over the M5, but the M9 Ultra only improves by 1.2x over the M7, that's my signal to buy. Unfortunately they haven't slowed down yet.
Recently took a Minisforum 7840hs PC out of rotation as a media PC and made it a full time coding workstation with Proxmox. I do a VM per project due to the nature of agentic editors.
I was using a VM setup on my MBP but it felt like a huge waste, having to leave a laptop on 24/7 when all it did was run Claude Code inside VMs.
I likely will stick with a Macbook Air 15" for next purchase, and beef up my "Claude Server" down the road.
Yep, this is my exact thought. The pendulum has swung back toward a desktop making more sense for me than a laptop. It all depends on whether there is anything useful to do with an amount of computation that can't be fit into a laptop package. For a long time there wasn't, now there is.
That’s nearly what I do but on a smaller scale. My iPad Pro serves as my laptop 90% of the time, and the 10% of the time I need to actually code and test in a chromium browser I remote into a mini.
Apple prices have always been insane, there is a reason why during the days it almost went bankrupt, in Europe it could not rival with PC, Amiga, Atari, Acorn.
Because who hates themselves that much? It's the thing I touch and interact with. That's exactly the part that needs to be sturdy, smooth, and pretty. It's the facade to the beast at the other end.
Also it'll be truly too slow. You need to at least be able to access a shared document while a video call is going.
The funniest recurring thing when working at Google was new hires getting baited into taking a Chromebook, then not being able to switch to a Mac for like 2 years. Our team made sure new people didn't fall for that.
Yes, except that the only way to get a fancy screen is also to put the fancy cpu in it. If there would be an Air with the screen of the pro I would buy it. Maybe even a Neo with that screen.
I’m doing essentially this, and got a MacBook Neo.
Fir kinda the first time in my life I don’t really have development tools on my personal laptop. I ghostty and openvpn client installed.
I have a large remote linux workstation (2x 8c/16t xeon cpus, 256gb ram, 2x8tb spinning rust disk) and i have my tools over there (along with some VMs).
It works surprisingly well.
Also, the macbook neo is a surprisingly capable little machine.
For a desktop you may find yourself better on a Linux or Windows machine price/performance wise.
I personally own an M3 ultra, an M1 max as laptops, but my desktop is a Ryzen desktop I built in 2022 and it was a third in price of the ultra for more power.
I was in the same situation, I used maxed out 15'' M3 Max MacBook Pro docked to Studio Display closed on vertical stand behind the screen. It was fine for office work, but running local LLMs would definitely overheat it. The battery started degrading purely due to heat issues. And it was audible as well.
I decided to get Mac Studio M4 Max, also all maxed out config and the cooling is so much better that I can run local LLMs like Gemma 3/4, gpt-oss 120b all day long without any heat issues or any audible fan noise. So for my use case it was the right decision. I subsequently added 15'' M5 Max MacBook Pro all maxed out to my collection and even though it is slightly faster on LLM inference (I get 100 tokens/s with Gemma 4 27b model), you just can't run LLMs longer than a few minutes. It starts overheating and gets really loud.
Weird, I’ve run LLM batch sessions for hours on my Max M3 MBP. It doesn’t get very loud, though I’m not getting anything close to 100 tok/s on a 27b model, I use a 35b MoE model just to get 90 tok/s. The fan comes on but thermally it never overheats. I do have it in a vertical closed position, though.
That’s what I have been doing for years, it remains in the house secured while I ssh into it from an old thinkpad. You can get air to pair it with it if you really wanna have that seamless flow, otherwise, ssh works well.
I'd never go x86 again after owning an m1. I'd have replaced an x86 laptop 2 or 3 times by now (2020 m1). My last $3500 dell xps 13z before buying the m1 was absolutely horrible.
Laptops can't do agentic engineering. They get hot as hell and battery drains instantly. I think this will promote a switch to desktops for the next couple of years, until we have new mobile chips.
"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 puts the NAND flash controller on package, so it cooled as part of the SoC/CPU as they share an IHS. Given it is part of the fabric it only has to maintain signal coherence on millimeter to micrometer scales, while enterprise/consumer NAND PCIe have to adhere to standards which force them to signal at 800-1200mV and keep that signal stable for centimeter scale distances.
Basically, Apple gets to cheat because they shove everyone onto the same IC & make the OS that runs on this SOC.
Im curious, how often is SSD / storage speed performance really useful? I feel like for many people it's akin to gigabyte wifi in that its nice to have, but not really particularly necessary
Apple’s “LLM in a flash” paper [1] sheds some light on why this can be a big deal, especially if they are working on codesign of model and hardware in this dimension.
It's very important. Every time you launch an app or open a file it's critical for performance. Also when memory runs out and the OS swaps to disk it makes a huge difference.
It's nice when using large sample libraries so you can stream them off the drive without as much caching in memory. Local LLM workflows probably also benefit from being able to run models too big for RAM off the drive.
10 grand for 256GB memory. Likely double that for 512GB, but won't be available or finalized until October. Thunderbolt 5 is highest bandwidth external IO available at 120Gb/s. 1.2TB/s claimed max internal memory bandwidth.
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.
That's in the same ballpark as two 128GB AI machines like the Asus GX10 or DGX Spark or Strix Halo. And, it seems very likely to perform better than either of those for inference. And, 256GB brings some pretty good models into play.
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.
About 20 years ago my dad bought me a $5k computer, it was future proof for about "5 years" before we had to upgrade its internal parts (more memory, new graphics card).
It was future proof but not really because it struggled a lot in its final years.
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.
Think it would have same memory bandwidth if the RAM was upgradeable?
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.
It isn't integrated into the motherboard, it's integrated onto the same package as the CPU/GPU which allows for better signal integrity and higher speeds. You can get somewhat close to the same speeds while modular with tech like LPCAMM2, but there are some pretty difficult challenges to overcome to close the gap completely. As an example, the Framework Laptop 13 Pro CPUs support up to 9600MT/s (same as M5), and Micron sells LPCAMM2 modules that can run at 8533MT/s, but the 13 Pro only officially supports 7467MT/s.
If it was upgradable, then yes, spending more on top of it every year would make it future proof, but that's not the point. It's that spending 10 grand doesn't get you a future proof computer today.
> The way the Apple M-series does ram that might be difficult to pull off.
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.
That actually would be interesting - yes, the computer itself is basically a PCB, but it’s also wrapped in a couple pounds of aluminum, a power supply, cooling fans, and a few other things that don’t need to be consumables. Upgrade a mini or a studio by swapping the new board into the old case - yeah, you’re not saving much money, but you also don’t need to throw out the entire rest of the case, and you can ship the main board in the space of a couple CD cases.
It’s a very non-Apple thing to do, but it’d be pretty awesome if they did.
> Framework for example managed to pull that off, and in mobile at that, where constraints are much worse than for a desktop computer.
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.
The relevant comparison isn't one mac studio to one RTX 6000, it's a 24 channel DDR5 system, which also has ~1.2TB/s of memory bandwidth (or more when Xeon 6 compatible 8800mt/s memory becomes widely available), vastly higher prefill due to more CPU horsepower, orders of magnitude faster networking, can hook into GPU accelerators, can be upgraded etc. A baseline 384GB system from eg Puget is ~30K vs ~12K for the 256GB Mac Studio and you do get value for the money.
It can be more than "slightly", particularly if the model you're interested in (or will be interested in in 6 months) doesn't fit on the mac studio. You also need to account for eg storing 10TB of random checkpoints, load time when experimenting, and so on. When you start actually needing throughput these are all capability gaps in practical use, not just x% benchmark differences.
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.
How's the compute side now, I wonder? Because while the Ultras have impressive memory bandwidth for inference, processing prompts still takes a dog's age on my M3 Ultra. I heard the M5 makes some strides forward in this area, though, and the M7 in particular promises to go a lot further.
M5 is excellent, they’ve finally gotten their own tensor cores.
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.
Except the RTX 6000 will run circles around the Mac studio in just about every way. Memory bandwidth is literally the only spec where Apple is competitive, and while high memory bandwidth is necessary for LLMs to perform well, many people strangely don't understand that memory bandwidth alone is not sufficient.
It's unclear to me how bandwidth scales with multiple connections. Many-to-many does not seem ideal. Daisy chaining would be fine for straight pipeline work. There doesn't seem to be an equivalent of a ethernet switch for thunderbolt 5 though.
Waited years for a decent Desktop lineup like this as I was hugely disappointed in the generation old M3 Ultra when it was released. Unfortunately it took Apple so long that the memory prices are now through the roof - USD $4000 for 164GB RAM upgrade is insane.
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.
> Apple’s most powerful Mac raises the bar for local AI
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.
Why doesn't Apple make a tower PC with a standard ATX motherboard, power supply, extension cards, etc, like in the old days? That's immensely more upgradable, easier to cool, and I don't believe most people expect their desktops PCs to be tiny.
The reason the mini & studio work as well as they do for the use cases that have made them popular again is because the architecture puts memory, cpu, and gpu/npu on the same die, and puts storage right next to it, which is why you get the storage & memory bandwidth you do. The separability of those components would break that, which is why the Mac Pro didn’t survive past one generation in the Apple Silicon era.
I'm actually coming around to realizing that I _do_ expect a desktop PC to be small. I'm finding myself only considering Mini ITX desktop cases when I think about upgrading my desktop. I only have one video card and don't have storage requirements that necessitate lots of 3.5" drives, a big nvme is all I need.
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.
The memory and GPU are integrated into the CPU so those can't be upgraded anyways. That's also how the memory can be so fast (shorter physical distance).
Sorry for being lazy, but is there a rough breakdown like "You get sonnet level for M5 and Opus for M5 pro, etc.", or is it still speculative. Or put simpler, do you get Opus level for the 256GB M5 Max?
For local LLMs with a Mac, rule of thumb is you always want an Ultra (due to memory bandwidth). Even an M1 Ultra is superior to an M6 Pro in this regard.
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.
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.).
I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.
To put this into a perspective, Google helpfully reminds:
> 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.
John Dvorak said many, many decades ago (80s/90s) that the computer you want will always cost $3000. That statement has been more/less true for some time periods than others, but with some wiggle room I’ve found it to be accurate enough.
Care to guess the approximate price of the MBP I bought earlier this year?
My heavily-upgraded M1 Max came in slightly over that when I got it five years ago. (Still going very, very strong.)
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.)
I buy large and run it into the ground so long I mistake the ground for the computer's remains.
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.
They still are, if what you want is roughly the same as the prior generations capability with some uplift (making then number up, but say 20% faster or more ram or whatever).
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.
1.2 TB/s bandwidth of M5 Ultra comes from two dies of M5 Max (each 614 GB/s) connected together using 4.4 TB/s inter-die fabric.
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
It looks like speculation that Apple would raise the base chip’s maximum RAM from 32GB to 48GB was wrong.
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:
They probably literally don't have enough NAND to go around. 768GB of memory (48GB x 16) is enough for nearly 100 iPhone 17s; that's $800k of iPhones at MSRP, although likely much lower margins than these high-RAM boxes.
> M6 supports up to 32GB of unified memory to multitask across demanding apps and run LLMs on device for secure and private agentic tasks. It also provides up to 170GB/s of unified memory bandwidth — a 10 percent increase over M5 and a 2.5x increase over M1.
Not a surprise this is launching now. John Ternus is taking the reigns as CEO in a week and was previously SVP of hardware engineering.
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.
Same reason they cut the big options on the existing models, this way they can sell more devices. The additional cost for the additional 512GB would have to make up for the loss of another sold device otherwise. No idea if there would really be that many people buying this then while on the other hand AI stuff makes people do crazy stuff, so...yeah :)
They seem to be suffering from the supply constraints like everyone else. They phased out the higher capacities on the M3 Ultra Mac Studio a while ago, and if you order a 128GB MBP, say, you're looking at six weeks or more for delivery.
They have no fab for CPUs, they are manufactured by Samsung and TSMC. The bottleneck is in manufacturing RAM not CPUs so there is nothing Apple can do here.
True, but you can link them up over thunderbolt or Ethernet. If your goal is to run local LLMs, not all weights need to live on the same computer. You can segment the workload by layers and pass the activations along the lower bandwidth interconnect with a small perf penalty. Also you get double the CPU/GPU cores allowing for better multi user/agent performance.
Neither is the right alternative to compare to. You aren’t going to hit 100% utilization (if you are, ignore me, this doesn’t some to you, and write a blogpost for me to read and share).
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.
My card (RTX Pro 6000) is always doing something all the time from my queue; like some synthetic dataset generation up next. I still actively use runpods and openrouter for scaled stuff, I was spending a bit and then did the maths, and invested in it.
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.
To experiment, its still al ot cheaper to prepare everything locally and then just rent a GPU Node on all of these non hyperscalers.
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.
Insta-leased. I’ve ran over 1 million prompts on ollama to determine “is X website”. I’m ready to use use bigger models locally to do more thinking now. I have zero desire to give Dario anymore than $20 a month after his “you all are gonna be mass unemployed” spiel.
Big ole pool of very fast ram that can be accessed by the CPU and GPU. Lets you run larger models. AMD does the same thing with Strix Halo. I have a 128gb machine at home, and have had difficulties running 120b models, but 70b and below run pretty well.
I wish they were offering 1TB of Unified Memory for the M5 Ultra. I already have an M5 Max MBP w/ 128GB of RAM for running local models, and while there's a /few/ models that I can run in 512GB that I can't run in 128GB that are interesting, where things really shift is at 1TB of memory which allows you run >1T parameter models w/ 4 bit quants reliably. 512GB is just on the edge of "enough", which is maybe the point of maximum frustration considering current memory prices.
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.
I'd consider a 1tb machine at 20k, but I'm not going to pick up a 256gb one at all. 1TB fits a frontier-ish model in memory without massive quantization, which is a very interesting capability for a non-rack piece of compute.
More likely double that, even. I think you'd still see many buyers there. You can spend like $16k alone on a RTX 6000 PRO with a mere 96GB of VRAM now..
I would probably spend up to $30k if I could get 1TB of Unified Memory, because it would allow me a guarantee to run pretty much any local model I want, including >1T parameter models with reasonable quants. I wouldn't be surprised if 512GB is close to $20k when it becomes orderable in October. The justification is less about absolute price and more about price to what it enables. 512GB really doesn't enable much over 128GB for me, but 1TB would massively change things.
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.
RDMA is buggy and Thunderbolt only delivers 1/10th the throughput of native connectivity. 1TB of Unified Memory w/ 1.2TB/s of bandwidth with marginally ~$30k cost is a different story than 1TB of sorta Unified Memory w/ an effective 120GB/s of bandwidth with a marginally ~$40k cost + all the RDMA bugs.
Depends on your perspective. People think nothing of spending 50-100K on a car that basically gets them to work. But the thing they use for day to day work then gets the evil eye when it costs more than 1K. It's slightly irrational. Not everybody needs a high end mac. But when you do, it sure is nice that you can get one.
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.
Nice for them to add Thread and 10G ethernet to base Mac Studio. If they allowed first class Linux, this could be a great home server machine. I ordered the base model. 512GB SSD scares me but would I even notice plugging in TB5 external drive?
Boy, oh boy Apple is the new shovel seller during AI gold rush.
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.
I dunno, Apple's been throwing many bones to their customers who use their Macs for AI stuff; like Apple working with, and signing TinyGPU's NVIDIA eGPU drivers.
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.
Wow, didn't know this exists. So instead of ditching my M1 Pro Macbook for a newer one with more RAM and power I could do this instead (if reasonable regarding pricing).
anyone know if this is "pre-order" is coming late October, or "will be available to ship in late October, thus pre-order will be available earlier than that"
Am I the only one that now finds press releases like this similar to "AI Slop"
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.
Makes managing both backups and handling failure scenarios involving loss or unauthorised access to the laptop less of a hassle as well.
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.
And that, from mental load standpoint, is not healthy for most folks.
If your computing needs line up, it's a very serviceable approach.
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.
I'm currently SSH-ing into my workstation from my M4 Air with 24 gb ram and it's ideal for this flow. Slack/editors/clients/browsers/etc. easily gobble up over 16 GB. I have no more dev tools/compilers/source on my client machines, everything is dockered up on remote workstation in isolated VMs (too much supply-chaining).
My only downside to using a pro is not having 120/4k HDMI port on air and my dock won't support it with Apple (it does with windows)
The issue (apart from Mac mini still having the old, bigger form factor back then) is that this requires a full shutdown (obviously), and that is more friction than opening a closed laptop lid. It just takes a moment for every app and background service etc. to settle back in after, and depending on how your brain works, you might not like that a whole lot.
It absolutely is a cool feeling to carry a pretty mighty desktop in the backpack, though.
iMacs are great for a lot of use cases, but my image of the typical HN user would prefer to keep the monitor separate.
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.
I’ll be selling my M4 MBA soon, I genuinely use the Neo more. Huge difference in typing experience.
Great repairability is a plus. It was super easy, and actually fun to open. Felt like unboxing an Apple product. Applied the thermal paste mod for $10 which works excellently; I’ve had it shortly after launch.
And I love the notchless display, even if I wished the color gamut was a bit better.
Having owned 3 MacBook Pros since 2008, the decision to make my next computer be a Mac Studio came down to (1) MacBook thermal throttling that slows down CPUs when it starts to overheat and (2) easier upgrade of Mac Studio SSD with after-market storage module whereas the MacBook requires more complicated disassembly and hot air gun to dislodge the surface mounted SSDs.
I have a brand new M5 Pro MacBook Pro I don't like it when the fans turn on. The Mac Studio will be faster and quieter for the same workloads.
Sorry for not being clearer. I don't like the MacBook's noise when the fans turn on.
The Mac Studio has bigger heat sinks to delay the need for thermal management -- and if its fan does need to turn on, the bigger size means it's still silent instead of the high-pitched whooshing noise the tiny fans make in the MacBook.
Most, if not all, of our current work happens on remote cloud vms. Now I'm stuck with carrying a 3KG monstrosity to work.Every day.
Absolutely no positives compared to my ThinkPad that weighed less than half in my previous job.
Remote development is "good enough" these days. With VS Code, Development containers etc... Having a light weight, portable laptop is so much nicer than a laptop that you can't even rest on your lap for long duration.
The only thing you need to be mindful of using light weight laptops is not having enough RAM to fit all your browser tabs..
Everything is a container or VM now, and none of it runs locally for me.
I have a desktop (older intel) with giant monitors and a keyboard for when I sit at the desk. I have the laptop for when I travel, go out or just want to work from the couch.
When I do my next upgrade to "better hardware" I'm not migrating a machine, rather I'm migrating the containers. My workflow is such that if I loose one of the boxes I sit at to a cup of coffee I really wont care other than the financial loss of a new laptop or keyboard.
The biggest win in all this was dumping the off the shelf firewall/router and moving to Opnsense. Wireguard vpn lets me route all my traffic through home for all my devices (and what is now a growing home lab).
There are scopes of work that this setup would not work for. I would not want to be a video editor with this set up, it's not ideal if you want to play AAA games. But for what I do, it is pretty ideal.
But in the end I ended op buying a Lenovo Legion and put Linux on it.
Laptops are so fast these days that I didn't want to be bothered with setting up connectivity to a remote desktop.
But if your laptop never leaves your desk I think a desktop computer is a great option. Relatively cheaper and easier to maintain and upgrade.
I'm waiting this out.
I was using a VM setup on my MBP but it felt like a huge waste, having to leave a laptop on 24/7 when all it did was run Claude Code inside VMs.
I likely will stick with a Macbook Air 15" for next purchase, and beef up my "Claude Server" down the road.
The funniest recurring thing when working at Google was new hires getting baited into taking a Chromebook, then not being able to switch to a Mac for like 2 years. Our team made sure new people didn't fall for that.
Fir kinda the first time in my life I don’t really have development tools on my personal laptop. I ghostty and openvpn client installed.
I have a large remote linux workstation (2x 8c/16t xeon cpus, 256gb ram, 2x8tb spinning rust disk) and i have my tools over there (along with some VMs).
It works surprisingly well.
Also, the macbook neo is a surprisingly capable little machine.
I personally own an M3 ultra, an M1 max as laptops, but my desktop is a Ryzen desktop I built in 2022 and it was a third in price of the ultra for more power.
I decided to get Mac Studio M4 Max, also all maxed out config and the cooling is so much better that I can run local LLMs like Gemma 3/4, gpt-oss 120b all day long without any heat issues or any audible fan noise. So for my use case it was the right decision. I subsequently added 15'' M5 Max MacBook Pro all maxed out to my collection and even though it is slightly faster on LLM inference (I get 100 tokens/s with Gemma 4 27b model), you just can't run LLMs longer than a few minutes. It starts overheating and gets really loud.
So a combination of a powerful desktop and a "cheap" laptop might indeed be attractive.
"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).
Basically, Apple gets to cheat because they shove everyone onto the same IC & make the OS that runs on this SOC.
[1] https://arxiv.org/abs/2312.11514
data processing, LLMs, model loading, MoE loading, etc, etc relies on very fast storage to keep your GPU saturated.
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.
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".
It was future proof but not really because it struggled a lot in its final years.
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)
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.
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.
https://news.ycombinator.com/item?id=49041256#49082206
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.
It’s a very non-Apple thing to do, but it’d be pretty awesome if they did.
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.
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.
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.
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.
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.
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.
Maybe $17k for a 512gig system that can do 1.2TB/s seems like a pretty good deal for a small office.
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.
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.
I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.
> 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.
Care to guess the approximate price of the MBP I bought earlier this year?
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.)
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.
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.
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....
It would be significantly cheaper to fly to a tariff-free country and buy there.
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
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
Isn't 170GB/s slow for bandwidth?
Compared to something like VRAM it's slow.
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.
256GB model is $10k and the 512GB version will probably be double
Seems like miscalculation. If they had their own fab for RAM, they could completely corner the market today.
Also see: https://apfel.franzai.com
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 $70k?
The spark’s ~250gb/s bandwidth doesn’t really count here.
The comparison should be against renting in the cloud for the duration of your task for training and research or using pay-per-api-call providers for general inference instead of buying your own hardware (and paying the electricity and cooling bills on top), because let’s face it, the models you want to use are probably the same ones available on inference providers (but, yes, some are more trustworthy than others).
Speaking as someone that does ML/AI research, you are essentially paying a huge premium for being able to just run your Python script at any time without setting up a deployment script and harness to run the job remotely, while your hardware sits essentially idle the rest of the time.
The only way to make the math work is if you rent your hardware in the background for inference while you’re not using it in anger, but despite all the startups and promises that has never become as streamlined as mining bitcoins or shitcoins used to be and they don’t pay out as much as they say they would. Renting your hardware for training is another option but doing that is a lot more involved, options are fewer and farther in between, you won’t get as much utilization out of it, and doesn’t let you feasibly abort running tasks at a moment’s notice.
The maths to me was basically equivalent to prepaying for 242 days of runpod pricing for the same GPU; and I reckon I'd be able to get 6+ years of use out of this card with 96GB.
Plus there's the resell value -- it's actually appreciated by ~50% since I bought it.
Plus I do really enjoy that it's 100% local. I wouldn't feel comfortable giving my agents this much information if inference wasn't 100% local.
I wouldn't get another one, I wouldn't have as much value, but one is definitely paying off for me on the financial side.
1-2$ / 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.
Only reason to buy this if you want to own your compute.
Experimentation and inference are all going to be cheaper on the cloud
https://www.apple.com/mac-mini/
So not as flexible as apple's unified memory.
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.
At that point just rent proper GPUs in the cloud, you'd have way more power and pay only what you use for.
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.
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.
But +4000$ for an additional 128GB of ram is simply milking the customers, as they know they will have many of them.
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.
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.
EDIT: AMD too, it's not limited to Nvidia, nice.
They're eating nvidia's lunch.
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.