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.
alfanick · 2026-08-25 13:12:19 UTC
Don't forget that US prices usually do not include the VAT, while EU prices usually do include respective VAT.
ilikehurdles · 2026-08-25 14:38:15 UTC
A lot of us in America have no sales tax (if that’s what you mean by VAT) and those that do have it at a fraction of EU VAT rates.
This is difficult to enforce, but it seems that "taking advantage" is strictly speaking just tax fraud.
nine_k · 2026-08-25 13:16:40 UTC
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.
mrala · 2026-08-25 13:38:52 UTC
It would be interesting to compare the costs of a top of the line machine every decade or so. Costs were steadily decreasing until recently.
jacobr1 · 2026-08-25 14:02:32 UTC
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.
mikestew · 2026-08-25 14:29:48 UTC
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?
seanmcdirmid · 2026-08-25 14:48:27 UTC
I bought my refurbished M3 Max MBP with 64 GB for $3k a couple of years ago. Before Ethan I never spent more than $2k for a computer.
mikestew · 2026-08-25 15:00:24 UTC
The “spend” and “want” number might differ, depending on one’s financial state. I know I’ve purchased plenty for less than $3K. But the one I wanted…
seanmcdirmid · 2026-08-26 00:43:20 UTC
I'm old and established (after spending most of my life not), but ya, I get what you are saying. It was a huge leap for me to spend $3k on a laptop.
Before local LLMs became a thing, I had completely lost interest in buying anything but the cheapest laptop. It felt like "personal computing" was a solved problem. But...it actually isn't, and this is exciting.
ahknight · 2026-08-25 14:59:20 UTC
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.)
mikestew · 2026-08-25 15:02:26 UTC
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.
rogerrogerr · 2026-08-26 03:43:29 UTC
I got a 64GB M1 Max four years ago or so, used. Felt like a ridiculous overspend at the time, but I'm sure smug about it now.
willtemperley · 2026-08-25 14:34:01 UTC
> I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.
It would be significantly cheaper to fly to a tariff-free country and buy there.
napolux · 2026-08-25 14:40:31 UTC
that's what I'm planning to do.
meerita · 2026-08-25 14:57:11 UTC
Where?
sroussey · 2026-08-25 22:17:16 UTC
Technically, California and other state have laws that say you must report this purchase and pay the tax the moment it enters the state.
gizajob · 2026-08-25 13:08:58 UTC
Bizarre there isn’t a 1TB RAM option hidden away for the excessively frivolous or VC funded.
gauntr · 2026-08-25 13:15:51 UTC
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 :)
MisterPea · 2026-08-25 14:18:56 UTC
Considering Apple pricing it actually might.
256GB model is $10k and the 512GB version will probably be double
petercooper · 2026-08-25 13:28:39 UTC
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.
hardb · 2026-08-26 02:58:16 UTC
It's worse than six weeks: Apple quoted me 10-12 weeks yesterday for an M4 Max Studio (about Nov 17) December for the M3 Ultra. Planning to lock in a new model soon. I went looking for used but those are wildly expensive. Strange times. https://hard.bargains/posts/mac-before-sept-22/
varispeed · 2026-08-25 14:11:04 UTC
It's more bizarre that Apple got caught with pants down. Focused on CPUs and ignored RAM.
Seems like miscalculation. If they had their own fab for RAM, they could completely corner the market today.
xdertz · 2026-08-25 14:23:57 UTC
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.
varispeed · 2026-08-25 18:12:39 UTC
Let me rephrase. They have not booked enough capacity at contract manufacturer.
gizajob · 2026-08-25 21:13:34 UTC
Recently Micron pointed that finger and threw that shade in Apple’s direction saying that their priority for years has been squeezing margins in their favour, so there wasn’t the slack in the system to build the fab capacity that is now desperately required given the sudden need for RAM now that there’s a cause to use it in AI Inference.
Sephr · 2026-08-26 01:59:15 UTC
Apple has a fab for CPU R&D. It's not for final production though.
mlsu · 2026-08-25 14:27:49 UTC
They don’t have their own fab for CPUs either.
actionfromafar · 2026-08-25 14:29:05 UTC
They would have had to start building that fab 5-10 years ago. It would have been incredible foresight to do so and it would have looked insane.
nythroaway048 · 2026-08-25 13:09:00 UTC
512GB unified memory option coming available in October.
marcuskaz · 2026-08-25 13:16:05 UTC
The 256GB option is +$4,000 - the overall price for 512GB setup would probably be $20k!
notnullorvoid · 2026-08-25 13:51:32 UTC
It needs to be a little less than double the overall price for 256GB option, otherwise it's better to get 2 256GB and link them.
Zylokloto · 2026-08-25 14:11:23 UTC
you can't link onchip memory.
notnullorvoid · 2026-08-25 14:35:48 UTC
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.
Zylokloto · 2026-08-25 14:51:36 UTC
Ah sorry you are right I missread what you meant by it.
nowittyusername · 2026-08-25 18:22:26 UTC
I was thinking the same as you as far as price per value, it does make seance to get 2x of these things IMO, but what throughput hit would you see in linking versus one machine? latency does matter, and there must be a trade off no?
ricardobayes · 2026-08-25 13:09:42 UTC
512GB unified RAM is going to be really good for running local LLMs.
tarr11 · 2026-08-25 13:12:02 UTC
What is unified ram? RAM and VRAM as one thing?
lynndotpy · 2026-08-25 13:20:18 UTC
Yep, exactly. It's just one shared pool of RAM with zero-copies necessary.
AbsurdCensor · 2026-08-25 13:23:43 UTC
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.
dannyw · 2026-08-25 15:28:34 UTC
AMD Strix Halo unified memory still requires allocating X to GPU, x to CPU at UEFI.
It’s more that it’s a very parallel architecture than fast.
The LPDDR5X under the hood is slower than what you’d find in a graphics card vram of years ago
That’s why you get consumer macs with 512gb while GPU makers are reluctant to give you more than 16gb unless you pay dearly. It’s not the same kind of mem
Zylokloto · 2026-08-25 14:10:32 UTC
In best case its also on-chip high speed ram.
fsuts · 2026-08-26 07:01:00 UTC
Yes
egonschiele · 2026-08-25 13:11:02 UTC
> 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.
Isn't 170GB/s slow for bandwidth?
blints · 2026-08-25 13:15:10 UTC
It is. That's the mac mini. For local LLMs you would want the Mac Studio, which tops out at 1.2TB/s.
tristor · 2026-08-25 13:16:35 UTC
Kinda. Strix Halo does 256GB/s of memory bandwidth, and is significantly slower than an M5 Max (614GB/s). Feels like intentional market segmentation?
kamranjon · 2026-08-25 13:22:55 UTC
You can get the m5 pro in the Mac mini with 307GB/s at 64gb of memory it’s $2899
scosman · 2026-08-25 13:21:18 UTC
It's fast by computer standards and excellent for entry level chip. The Pro/Max/Ultra chips are always faster.
The thread you're replying to is asking about the 170GB/sec memory bandwidth of the base M6, not the faster spec of the Ultra chips.
mkesper · 2026-08-25 13:22:42 UTC
For max memory bandwidth you need to buy the Ultra versions (M5 Ultra: 1,2TB/s, this gets comparable to real GPUs regarding the memory bandwidth).
matja · 2026-08-25 13:29:18 UTC
It's higher bandwidth than any dual-channel DDR5 desktop machine, but Apple never quote the memory latency, so hard to compare otherwise.
geraneum · 2026-08-25 14:42:57 UTC
Would that be a difficult comparison to do fairly sine one is SoC and the other isn’t?
matja · 2026-08-25 15:53:04 UTC
I meant that it's a difficult comparison between platforms without having all the details like memory latency, how the memory controller load increases latency (can increase by 4x on some platforms), cache latency, TLB entries, etc.
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.
kamranjon · 2026-08-25 13:30:13 UTC
You would want to get the M5 pro version with 307gb/s if you were interested in running local LLMs.
diabllicseagull · 2026-08-25 14:48:04 UTC
M6 and M5 Ultra both have comparable memory bandwidth per GPU core. I think they will perform well.
joshstrange · 2026-08-25 13:11:06 UTC
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.
appplication · 2026-08-25 13:23:26 UTC
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.
Gareth321 · 2026-08-25 13:35:11 UTC
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.
dannyw · 2026-08-25 13:53:25 UTC
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.
havaloc · 2026-08-25 17:09:23 UTC
The Neo keyboard just feels nicer than even an M5 Air.
tamimio · 2026-08-25 13:26:59 UTC
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.
super_mario · 2026-08-25 13:28:17 UTC
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.
seanmcdirmid · 2026-08-25 14:43:55 UTC
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.
jermaustin1 · 2026-08-25 13:28:20 UTC
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.
simonh · 2026-08-25 13:31:39 UTC
Buy in 2 years, or buy now and have it last 2 years less than forever.
jubilanti · 2026-08-25 13:34:52 UTC
Then you'll always be waiting, there's always something new the industry tries to tempt you with.
jermaustin1 · 2026-08-25 14:19:45 UTC
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.
Gareth321 · 2026-08-25 13:37:11 UTC
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).
I'm waiting this out.
ahknight · 2026-08-25 14:40:46 UTC
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. :/
xhkkffbf · 2026-08-25 15:10:37 UTC
My desktop with 64gb of RAM has been my best performing financial asset. The value keeps rising.
JohnBooty · 2026-08-25 17:39:01 UTC
If running LLMs locally matters, it’s hard to imagine a “forever machine” existing in anything less than 5-10 years, probably more. This stuff is just evolving so rapidly. Buying a “forever machine” today might be like buying a “forever GPU” in 2003.
ape4 · 2026-08-25 13:29:04 UTC
How about business where you send in all your old devices and get back a SSD using using their memories
try-working · 2026-08-25 13:35:25 UTC
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.
steve1977 · 2026-08-25 13:40:31 UTC
But laptops can remote into boxes that can run agents.
So a combination of a powerful desktop and a "cheap" laptop might indeed be attractive.
jonathanberger · 2026-08-25 13:47:44 UTC
Are you referring specifically to agentic engineering with locally hosted models?
hectdev · 2026-08-25 13:45:49 UTC
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.
hirvi74 · 2026-08-25 13:47:28 UTC
Do it! I went with the Mini/Neo combo. I don't need MBP power when out and about. When at home, the Mini is all I use.
jgwil2 · 2026-08-25 13:49:58 UTC
If all you want to do is remote into your desktop, Neo seems like overkill. Why not just get a $200 Chromebook and save yourself $500?
rjrjrjrj · 2026-08-25 14:06:07 UTC
Because the screen, keyboard, and especially trackpad on a $200 Chromebook sucks?
bredren · 2026-08-25 14:10:16 UTC
Also: the enclosure, and the hinges.
frollogaston · 2026-08-25 15:08:53 UTC
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.
ahknight · 2026-08-25 14:42:00 UTC
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.
PennRobotics · 2026-08-25 15:45:38 UTC
This comment got me curious, so I searched for cheap laptops with mobile internet. There's at least one LTE Chromebook now for about 300 euros. This might be my next laptop if it can run Tailscale and remote desktop.
olyjohn · 2026-08-26 01:37:27 UTC
Also remoting into a Mac sucks on anything that isn't a Mac. It runs like shit when using any VNC client that isn't Apple's.
Comments
I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.
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....
https://tax.idaho.gov/taxes/sales-use/use-tax/online-guide/
This is difficult to enforce, but it seems that "taking advantage" is strictly speaking just tax fraud.
> 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.
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.
Care to guess the approximate price of the MBP I bought earlier this year?
Before local LLMs became a thing, I had completely lost interest in buying anything but the cheapest laptop. It felt like "personal computing" was a solved problem. But...it actually isn't, and this is exciting.
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.
It would be significantly cheaper to fly to a tariff-free country and buy there.
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.
So not as flexible as apple's unified memory.
It’s more that it’s a very parallel architecture than fast.
The LPDDR5X under the hood is slower than what you’d find in a graphics card vram of years ago
That’s why you get consumer macs with 512gb while GPU makers are reluctant to give you more than 16gb unless you pay dearly. It’s not the same kind of mem
Isn't 170GB/s slow for bandwidth?
Compared to something like VRAM it's slow.
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’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 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.
I'm waiting this out.
So a combination of a powerful desktop and a "cheap" laptop might indeed be attractive.
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.