Apple Silicon Mac Pro Configurations: Everything We Know

[theluggage]

What if one of the ARM-64 CPU makers (such as under license from Qualcomm) were to begin offering a DIY ARM ATX desktop motherboard that could at least run "bare metal" Windows ARM-64, as well as potentially dual-boot macOS? Thus allowing for a Hackintosh running on ARM?

Sadly, I doubt that "Hackintosh" on ARM will ever be a thing. Like Bootcamp, It worked because, up to 2016, Intel Macs were pretty much PC clones with nice cases and trackpads, using mostly PC hardware - so MacOS had drivers for Intel disc controllers and GPUs, AMD GPUs, Broadcom sound chips etc. Apple's T2 chips changed that somewhat by taking over a lot of functions like disc controller, but pre-T2 Macs were being sold until 2020 so "generic" Intel hardware is still supported - but the only thing supported on ARM is the Apple Silicon System-on-a-chip.

The writing was on the wall for Hackintosh anyway with the T2 chip - that clock started ticking when the 2020 T2 iMac was released.

There has been mention of Apple using unpublished calls for their ARM instruction set.

It's not just the instruction set - most of the functions done by generic PC hardware on pre-T2 Macs are now handled by proprietary hardware on the Apple Silicon system-on-a-chip - AFAIK there aren't even any ARM graphics drivers for anything other than Apple's GPU. Plus there's the secure boot system & "secure enclave" on Apple Silicon chips that MacOS-on-ARM requires.

Didn’t they have something awhile back where you had to scavenge from a Mac (I think it was a ROM chip?), BUT you could then run Mac software on it… maybe it was just a dream?

No, you're not dreaming - there were products like that for the Atari ST and Amiga (since they all used 68000 processors): https://en.wikipedia.org/wiki/Spectre_GCR

...but that was back in much simpler times, before Apple was making its own processors... and when MacOS was MacOS, not son-of-NeXTStep.

 

[George Dawes]

Since the Apple silicon chips run so cool , wouldn’t it be great if they brought out a micro Mac Pro like Steve had on his desk ?

 

[toke lahti]

To make a "pro workstation" (not "worst station"), Apple needs to:

#1 Make RAM (Great again!) upgradeable
This would just need another level of ram to the system.
There's that faster ram in SiP and slower ram outside of SiP.

#2 Allow use of discreet GPU
This could (and should) be done via TB also.
Known as eGPU.
This shouldn't be too hard, since we have had 2 gpu configs for years.

Would this happen noly when they reach to M3 and MP-M3 will debute somewhere in 2026?

 

[Canubis]

I have A LOT of apprehension with the rumours of a reduced size [volume] MacPro. The whole point of the professional end of the market is to use specialist PCI-e cards like sound cards, capture cards etc.

You can’t fit those in a smaller unit. So it would effectively be a Mac Studio in a tower format.

The MacPro 2019 is a really an industrial design masterclass. The collaboration and engineering that went into it were unprecedented for Apple. To turn around and provide one that can’t be used with all the professional hardware would seem incredibly foolish.

I really fail to see a market spot for another tiny Mac Pro – now that Apple already has the Mac Studio out. In my opinion the Studio is the tiny Mac Pro we heard the rumors about.
If not for expandability i.e. with PCI-e cards, what's the goal of releasing another Mac model for Pro users with a different design?
The Studio was already designed with a huge cooling system, I'd be really surprised if Apple designed the Studio so poorly that it won't be able to house an M2 or M3 ultra in the future… I can see Apple adding something extra to the Studio, like more ports and then call it Mac Studio Pro or Mac Studio Max – this would fit their current naming terminology…

But if they keep bringing us a real Mac Pro with AS – which they already explicitly teased us with – I fail to see a niche in the market, if not for expanability. Either through industry standards like PCI-e, or something proprietary… like the MPX modules. This would ensure expandability to at least some degree while keeping cashflow close to Apple…

Something I could imagine for a new AS Mac Pro is a new connector similar to UltraFusion, which they use right now to "connect" 2 M1 Max to make an M1 Ultra. If Apple can connect 2 of their M1 chips together at great performance, why shouldn't this also work with other components. Something like that could possibly work for adding extra RAM later, but not regular RAM as we know it from the Mac Pro today, but some special SOC RAM components that we can get only from Apple – and of course with a premium price tag…

 

[Unregistered 4U]

#2 Allow use of discreet GPU
This could (and should) be done via TB also.
Known as eGPU.
This shouldn't be too hard, since we have had 2 gpu configs for years.

Would this happen noly when they reach to M3 and MP-M3 will debute somewhere in 2026?

Well, currently, #2 can’t be done because the GPU has to be in the same package as the CPU. All of Apple’s software and all software developed by third parties assume this is the case. Moving the GPU away from that shared memory will break the apps and would cause Mac Pro graphic performance to be even worse than the M1 Air.

BUT, IF Apple decides to make an update during a future WWDC to tell developers “Remember all those performance benefits we’ve been saying you get from the unified memory? Well, forget that! How would you like to instead have slower performance over a MUCH slower interface using cards from the likes of AMD and… AMD? Well, this WWDC is for you!” then, sure, they could come back.

 

[theluggage]

Since the Apple silicon chips run so cool , wouldn’t it be great if they brought out a micro Mac Pro like Steve had on his desk ?

Cool - but I'm guessing that's a hard drive enclosure (looks about the right size). However, you're not going to fit 6-7 PCIe cards and a couple of hard drives in there. If it's not going to have PCIe slots etc. then it needn't be any bigger than a Mac Studio.

 

[SFjohn]

The scaling and performance of the M1 Ultra and above failed to achieve the design goals as the way cross-die data is received causes an unexpected interaction; the raw interface between them is not the limiting factor. Apple seemed to have hoped that this bottleneck (albeit more akin to an instability at higher workloads) could be ironed out in firmware but this did not come to pass. As a result the M1 Ultra is unable to flex its muscle, the maximum power draw is constrained well-below the design's TDP and, as a side-effect, the thermal load never made it to the level that required the expensive and rather exotic cooler in the Studio.

This unexpected issue is undoubtedly a major driver to the delay of the ASi MP and effectively forced the move to M2-based processors for the multi-SoC Mac Pros. As I understand it, the M2 multi-SoC systems do scale proportionally and should provide exceptional performance. Those I speak too are very happy with their work.

So the M1 doesn’t go as fast as Apple hoped (on the Ultra) and the M2 version is really going kick ass?

 

[TECK]

I’d be really surprised if Apple released another Intel Mac. However I’d like it because it’d mean that my current Mac will have a longer support period.

I really don't know what to do, in terms of purchasing current 7,1 refurbished or hoping for a new Intel model. I'm 90% sure the new Mx based Mac Pro will not be as expandable as the 7,1 Intel model. They will repeat the 6,1 history with Mx chips instead. On the other hand, Apple might muscle the current 7,1 Intel owners by abruptly stopping software and security support. We could end-up with 7K spend (base model) for another 3 years support, being forced to move to Mx chips.

 

[TECK]

View attachment 2044783

Since the Apple silicon chips run so cool , wouldn’t it be great if they brought out a micro Mac Pro like Steve had on his desk?

That's probably a disk enclosure, shaped like a Mac Pro.

I'm guessing that's a hard drive enclosure

Sorry, did not see your post.

 

[SFjohn]

I really don't know what to do, in terms of purchasing current 7,1 refurbished or hoping for a new Intel model. I'm 90% sure the new Mx based Mac Pro will not be as expandable as the 7,1 Intel model. They will repeat the 6,1 history with Mx chips instead. On the other hand, Apple might muscle the current 7,1 Intel owners by abruptly stopping software and security support. We could end-up with 7K spend (base model) for another 3 years support, being forced to move to Mx chips.

I think Apple could keep a more advanced and expandable INTEL Mac Pro around. It won’t be as fast as the Apple Silicon Mac Pro. Anything’s possible, only time will tell…

 

[TECK]

I think Apple could keep a more advanced and expandable INTEL Mac Pro around. It won’t be as fast as the Apple Silicon Mac Pro. Anything’s possible, only time will tell…

I need a powerful Mac which allows me to use Windows also, I'm sure there are many users in my situation. I have not owned a PC since 2012, I never looked back since I switched to a Mac.

 

[avkills]

Not a Mac. I have a GPU server at work with 8x GPU’s each with 40GB

Super cool. I figured you might answer this way. What cards you using? (A6000?)

 

[Snahbah]

No sh--, Sherlock

Well, it seems to be a concept beyond your grasp. There is a a huge need for extremely powerful computers in some sectors, like mine, where price is a secondary conversation. They fact that they are also beyond your reach, doesn't deserve ridicule. So it would be great if you, well, jogged on little man.

 

[Snahbah]

To make a "pro workstation" (not "worst station"), Apple needs to:

#1 Make RAM (Great again!) upgradeable
This would just need another level of ram to the system.
There's that faster ram in SiP and slower ram outside of SiP.

#2 Allow use of discreet GPU
This could (and should) be done via TB also.
Known as eGPU.
This shouldn't be too hard, since we have had 2 gpu configs for years.

Would this happen noly when they reach to M3 and MP-M3 will debute somewhere in 2026?

I have a strong feeling there will be some sort expansion (both RAM and some sort of PCIe equivalent, no doubt Apple with make this proprietary and bloody expensive.

 

[dogstar]

I need a powerful Mac which allows me to use Windows also, I'm sure there are many users in my situation. I have not owned a PC since 2012, I never looked back since I switched to a Mac.

This. This is a unique market Apple can continue to cash in on with very little effort. They have the amazing case and system just designed in 2019. Just design a new MP motherboard with a killer new Thread Ripper processor and many people will buy for the optional Windows support as well as having access to all the PCIE cards and drivers out there. I just don’t see how Apple can replace the whole ecosystem they have built up by putting out some sort of Mx Mac Pro. It will disappoint so many people.

check out the specs on the latest Threasripper:

AMD Ryzen Threadripper Pro 5000 WX-Series Specifications

	Cores / Threads	MSRP/SEP	Base / Boost (GHz)	L3 Cache (MB)	TDP	PCIe
Threadripper Pro 5995WX	64 / 128	$6,499	2.7 / 4.5	256 (8CCD + I/OD)	280W	128

 

[SFjohn]

This. This is a unique market Apple can continue to cash in on with very little effort. They have the amazing case and system just designed in 2019. Just design a new MP motherboard with a killer new Thread Ripper processor and many people will buy for the optional Windows support as well as having access to all the PCIE cards and drivers out there. I just don’t see how Apple can replace the whole ecosystem they have built up by putting out some sort of Mx Mac Pro. It will disappoint so many people.

check out the specs on the latest Threasripper:

AMD Ryzen Threadripper Pro 5000 WX-Series Specifications

	Cores / Threads	MSRP/SEP	Base / Boost (GHz)	L3 Cache (MB)	TDP	PCIe
Threadripper Pro 5995WX	64 / 128	$6,499	2.7 / 4.5	256 (8CCD + I/OD)	280W	128

Maybe Apple will do that, maybe they won’t. Apple already disappoints the majority of people that choose Android phones. Apples’s business model is to disappoint the majority of people, and delight a minority, which is clearly working for them. Personally I hope you’re right, and Apple continues to make even better INTEL Mac Pros. Is there a large enough market for them? Only time will tell.

 

[curnalpanic]

Since the Apple silicon chips run so cool , wouldn’t it be great if they brought out a micro Mac Pro like Steve had on his desk ?

That seems to be a scale model of a Powermac G5. Maybe a birthday gift from Jony?

 

[MajorFubar]

Well, it seems to be a concept beyond your grasp. There is a a huge need for extremely powerful computers in some sectors, like mine, where price is a secondary conversation. They fact that they are also beyond your reach, doesn't deserve ridicule. So it would be great if you, well, jogged on little man.

It really couldn't have been possible for you to have misinterpreted my original post more, which was basically saying the EXACT SAME THING as you: they are halo products, selling in comparatively small quantities, and so, least likely to be stocked in an Apple Store.

But hey never mind.

 

[Macintosh IIcx]

The scaling and performance of the M1 Ultra and above failed to achieve the design goals as the way cross-die data is received causes an unexpected interaction; the raw interface between them is not the limiting factor. Apple seemed to have hoped that this bottleneck (albeit more akin to an instability at higher workloads) could be ironed out in firmware but this did not come to pass. As a result the M1 Ultra is unable to flex its muscle, the maximum power draw is constrained well-below the design's TDP and, as a side-effect, the thermal load never made it to the level that required the expensive and rather exotic cooler in the Studio.

This unexpected issue is undoubtedly a major driver to the delay of the ASi MP and effectively forced the move to M2-based processors for the multi-SoC Mac Pros. As I understand it, the M2 multi-SoC systems do scale proportionally and should provide exceptional performance. Those I speak too are very happy with their work.

I think something else is up beside any cross-die data issue. Something is not quite right with the GPU scaling on the M1 Max either, going from 24 to 32 GPU cores doesn’t always show the expected scaling. CPU scaling on the Ultra, on the other hand, looks fine.

I’m personally most interesting in whether they will be able to improve the GPU scaling on the M2 Max as that is imperative to the success of the Mac Pro with a 4x M2 Max setup (M2 Extreme or whatever they will call it)

 

[theluggage]

This. This is a unique market Apple can continue to cash in on with very little effort.

The downside of that is that they'd have to put in the effort to keep MacOS on x86 supported (including up-to-date drivers for the latest third-party graphics cards etc.) - whereas they're already building Apple Silicon-only features into Monterey and - if they finally drop the Intel Mini and Pro in the next 6 months or so - could probably get away with dropping x86 support starting with MacOS 14.

The other problem is that it would leave an "out" for software developers not to optimise their pro products for Apple Silicon, especially those products that already run acceptably on M1 Pro/Max but need work before they can squeeze all the juice out of an Ultra (or the rumored Extreme).

The reality is that, fundamentally, there's not much you can do on an x86 Mac that you can't do on a generic x86 PC - the 2019 Mac Pro had a bit of a head start by being an early adopter of the 2019 Xeon-W chips with insane RAM and PCIe capacities - but that tech is available to PC workstations too (the MPX slot design makes the plumbing much neater, but you can still plug comparable GPUs into a PC).

Short-term, I'm not denying that there are users for whom switching to Windows isn't viable today - but in the long term, that customer base of dedicated Mac users will slowly dry up as Mac evangelists retire and the bean counters & cloud computing enthusiasts win the arguments. Plus there's always a huge incentive for Mac-only software houses to make PC versions of their wares and work to bring them up to parity. Unless there is a supply of new professional Mac Users attracted by Macs either doing things that you just can't do on PCs or offering power in form factors that PCs can't match. That's hard to achieve with what is ultimately just a Xeon or Threadripper tower with current AMD GPUs - running an arguably nicer GUI that disappears as soon as you full-screen your cross-platform application.

There is one thing that Apple can do that Microsoft/Intel/Dell/HP/Lenovo can't - and that is to say "OK, we're switching to our own ARM-based systems-on-a-chip and it will take about 2 years to transition the whole range". That's their best long-term chance for being able to offer unique products that don't have to compete with commodity PC hardware.

(E.g. the Mac Studio doesn't have to be the fastest PC/GPU combo on the planet until someone comes up with a near-silent PC the size of a lunchbox that can rip through video editing at a comparable rate while burning <~200W)

 

[dogstar]

Maybe Apple will do that, maybe they won’t. Apple already disappoints the majority of people that choose Android phones. Apples’s business model is to disappoint the majority of people, and delight a minority, which is clearly working for them. Personally I hope you’re right, and Apple continues to make even better INTEL Mac Pros. Is there a large enough market for them? Only time will tell.

Honestly I feel like most people use Android cause it’s cheap, not because it’s better. I think Apple will always disappoin on price, but that’s just tough. Apple caters to the high end, always has.

 

[dogstar]

The downside of that is that they'd have to put in the effort to keep MacOS on x86 supported (including up-to-date drivers for the latest third-party graphics cards etc.) - whereas they're already building Apple Silicon-only features into Monterey and - if they finally drop the Intel Mini and Pro in the next 6 months or so - could probably get away with dropping x86 support starting with MacOS 14.

The other problem is that it would leave an "out" for software developers not to optimise their pro products for Apple Silicon, especially those products that already run acceptably on M1 Pro/Max but need work before they can squeeze all the juice out of an Ultra (or the rumored Extreme).

The reality is that, fundamentally, there's not much you can do on an x86 Mac that you can't do on a generic x86 PC - the 2019 Mac Pro had a bit of a head start by being an early adopter of the 2019 Xeon-W chips with insane RAM and PCIe capacities - but that tech is available to PC workstations too (the MPX slot design makes the plumbing much neater, but you can still plug comparable GPUs into a PC).

Short-term, I'm not denying that there are users for whom switching to Windows isn't viable today - but in the long term, that customer base of dedicated Mac users will slowly dry up as Mac evangelists retire and the bean counters & cloud computing enthusiasts win the arguments. Plus there's always a huge incentive for Mac-only software houses to make PC versions of their wares and work to bring them up to parity. Unless there is a supply of new professional Mac Users attracted by Macs either doing things that you just can't do on PCs or offering power in form factors that PCs can't match. That's hard to achieve with what is ultimately just a Xeon or Threadripper tower with current AMD GPUs - running an arguably nicer GUI that disappears as soon as you full-screen your cross-platform application.

There is one thing that Apple can do that Microsoft/Intel/Dell/HP/Lenovo can't - and that is to say "OK, we're switching to our own ARM-based systems-on-a-chip and it will take about 2 years to transition the whole range". That's their best long-term chance for being able to offer unique products that don't have to compete with commodity PC hardware.

(E.g. the Mac Studio doesn't have to be the fastest PC/GPU combo on the planet until someone comes up with a near-silent PC the size of a lunchbox that can rip through video editing at a comparable rate while burning <~200W)

I guess what I’m saying is Apple makes some of the best engineered PC servers on the market. Even if people just used them to run Windows I still think they would be highly desirable just for the quality of the hardware workmanship and engineering and so forth. It sort of keeps an open arm towards to the PC community as well, which is probably good so they don’t become too isolated.

 

[Unregistered 4U]

Apple already disappoints the majority of people that choose Android phones. Apples’s business model is to disappoint the majority of people, and delight a minority, which is clearly working for them.

Yeah, of the over 6 billion folks in the world, Apple’s goal for the Mac is somewhere between 20 and 30 million. If they can get those many folks to buy Macs without Windows compatibility, then, at that point, Windows compatibility is no longer something they need to be concerned with, regardless of how many current customers want it.

 

[dogstar]

Yeah, of the over 6 billion folks in the world, Apple’s goal for the Mac is somewhere between 20 and 30 million. If they can get those many folks to buy Macs without Windows compatibility, then, at that point, Windows compatibility is no longer something they need to be concerned with, regardless of how many current customers want it.

I’m pretty sure Apple wouldn’t mind Microsoft eventually releasing a Windows version that supports the M1. They are already supportive of Linux being installed on their M1 systems (see Asahi Linux). I think PCs will eventually head over to ARM or RISCV. It just seems the tide is inevitably turning that direction. May be a decade though.

 

[dogstar]

View attachment 2044783Since the Apple silicon chips run so cool , wouldn’t it be great if they brought out a micro Mac Pro like Steve had on his desk ?

This actually wasn’t the first Mac prototype sitting around in Steve’s office!