Apple M1 Pro Review - Is It Really Faster than Intel/AMD?

[MauiPa]

"exorbitantly expensive". is everyone else as tired of hearing this stupid unsubstantiated claim as I am? to validate I went to the Dell web site and "built" some XPS machines to see if the were so cheap that they could not be exorbitantly expensive. Guess what? the M1 air and MBP beat any Dell XPS on price, performance, quality of screen, Ssd speed, weight and battery life, and the XPSs are renowned for thermal throttling. Next I did the same thing with the 14 and 16 MBP. Guess what? same thing.

So enough already. If you think I am wrong, do it yourself, You constantly have to up features to get a CPU/GPU that is close in performance (before throttling), and then the build price is .....wait for it.....exorbitantly expensive.

 

[Homy]

I think the base M1 Pro performed very well in the video considering the circumstances, "crushing" the x86 laptops as he said himself, even though it was a mixed bag. The mistake he did was to compare the prices. First he says it's not a review and doesn't compare the other features MBP has but still compares the price at the end. Finally the price doesn't matter. If you like Mac there's only Apple and if you like Windows you buy pc. The only problem for Apple is it's hard to convert pc users to Mac with those high prices, as he also noted in the video, but many times a similar equipped pc with the same features costs about the same.

 

[MauiPa]

I don't know about Matlab, but Excel? It may be ARM native, but it's notoriously much slower on intel macOS than on Windows.

and lacking in features. You think there is a plan there. thank-you Microsoft, Lakshimash!

 

[JMacHack]

M1 Pro isn’t as amazing as some trying so hard for people to believe

show me on the doll where Apple Silicon touched you.

 

[MauiPa]

comparing a i7-11800H CPU to the M1 Pro is pathetic. Why not upgrade the CPU to an equivalent performer? Oh, you whole argument about how expensive the MBP is dissolves. For reference, the 8-core version of the M1 Pro is at least 10% faster, the 10-core version is about 40% faster.

Why benchmark a bunch of apps that are not written for ARM but are running on emulation? impressive as it is that they run and actually perform well, it is a ridiculous assertion

Why try to paint this video as fair when it is not

 

[MauiPa]

show me on the doll where Apple Silicon touched you.

LOL

 

[JMacHack]

Also, watching the video, I have a lot of respect for HW unboxed. They’re very no-nonsense when they talk about things. Still I have some criticisms of the video.

1. The goalposts. The M1 pro (not max) is trading blows with top of the line desktop processors, while using less power, as Apple advertised.

The fact that this 10-core cpu is punching at top of the line desktop cpus is impressive, no matter how it’s sliced. The goalposts have moved from “most performant laptop cpu” to “most performant desktop cpu”.

Which the tests do not lie. The top of the line desktop cpus from AMD and Intel manage to beat the M1 Pro. However put into perspective I’d still say the M1 series warrants the praise it received.

2. Methodology, in the video Steve himself said that it’s difficult to compare because of the difference in architecture and programs. He is correct, there’s no guarantee that any program uses the features of any cpu, and Apple Silicon being new, should take that into consideration.

3. Price, he’s right about the ridiculous prices for ram and storage upgrades, but this introduces another variable to the testing. The review sometimes flip flops between “better ultimate performance” (in the case of the cpu tests), and “best for money”. If we wanted to talk ultimate performance, then the top of the line cpu would need to be tested. If we’re talking price, then the comparable windows laptops should be tested.

The review is good in general, but doesn’t come off as a truly objective take on the M1 series, but more as a video to “own the fanbois”. I don’t think it does any service to hwub.

 

[Analog Kid]

I don’t think it does any service to hwub.

By giving grist to threads like this, I'm sure it's helping to bring in clicks. I won't be one of those clicks, but from what I'm reading here it seems that this is less of a "real world test" and more "if you move your Windows workflow to an Apple MBP, you essentially lose nothing while you transition to better optimized applications" message.

Do they do comparison benchmarks to show what happens if you move your Mac apps and workflow to that Intel machine? What's its performance in translating ARM instructions to x86 and virtualizing MacOS?

 

[JMacHack]

By giving grist to threads like this, I'm sure it's helping to bring in clicks. I won't be one of those clicks, but from what I'm reading here it seems that this is less of a "real world test" and more "if you move your Windows workflow to an Apple MBP, you essentially lose nothing while you transition to better optimized applications" message.

Do they do comparison benchmarks to show what happens if you move your Mac apps and workflow to that Intel machine? What's its performance in translating ARM instructions to x86 and virtualizing MacOS?

I don’t mind giving hwub clicks honestly. They’re up there in pc hardware reviews with Gamers Nexus.

 

[TechRunner]

speakers that sound like a wasp in a tin can

This made me laugh out loud. Great description!

 

[Ethosik]

"exorbitantly expensive". is everyone else as tired of hearing this stupid unsubstantiated claim as I am? to validate I went to the Dell web site and "built" some XPS machines to see if the were so cheap that they could not be exorbitantly expensive. Guess what? the M1 air and MBP beat any Dell XPS on price, performance, quality of screen, Ssd speed, weight and battery life, and the XPSs are renowned for thermal throttling. Next I did the same thing with the 14 and 16 MBP. Guess what? same thing.

So enough already. If you think I am wrong, do it yourself, You constantly have to up features to get a CPU/GPU that is close in performance (before throttling), and then the build price is .....wait for it.....exorbitantly expensive.

I’m right there with you. I have been putting up with those remarks for over 10 years now. It was funny when people reported that they could build a better computer than my 2010 Mac Pro was and at the time the Xeon processor alone was more expensive than what those user’s were saying they could build a PC.

 

[Ethosik]

People also need to realize that most power hungry laptops performance TANKS when it’s on battery. Even with high performance mode there are differences. Apple has always offered as close to full performance on battery as possible.

 

[collin_]

M1 Pro and x86 processor trades lead one after another. M1 Pro isn’t as amazing as some trying so hard for people to believe, but code compiling has been in its own league smoking all x86 competitors.

For me it’s about much more than just raw performance. I really like features such as the instant wake, silky smooth experience, longer battery life, much higher minimum graphics performance, substantially less heat and fan noise, no lag spike when switching between integrated and dedicated GPU (because there isn’t one), etc. -- all of the benefits that come from moving to ARM and an SoC architecture.

I don’t necessarily view Apple Silicon SoCs as like… futuristic. I view them as what a computer should be. I think x86 is antiquated and that the transition away from it was long overdue. Ever since the A11 Bionic benchmarks leaked I was like yeah… x86 is done for (and thank god it finally is). It was just mind blowing performance, especially for that time, from a chip with a 5 watt TDP.

 

[mi7chy]

Normal people on Mac don't run Matlab... nor do they run 7zip. Heck, 7zip doesn't even exist on Mac. We have Keka. Just the fact that you mentioned 7zip is already a signal to me that you don't use a Mac computer on a regular basis (or at all).

7zip is available on ARM MacOS. It's the defacto cross-platform standard that superceded rar and zip. Keka should be named Kaka.

https://sourceforge.net/p/sevenzip/discussion/45797/thread/ba29828ce0/

 

[jz0309]

I’ve given up on the X86/64 comparisons now, there seems little logical reason to it anymore.

If we’re Apple users, and considering this is MacRumors I’d guess many of us are (though I do still have a WinTel rig as well), then it makes no difference what the other side of the fence does, we’re not going to get it. Apple have moved on, personally I think for the better in the long run.

The only benefit now to Intel, AMD, Qualcomm and even ARM making advances is that it pushes their competitors. I’m all for Intel making better, faster (and hopefully more energy efficient) chips. But only because it’ll keep the pressure on Apple to improve Apple Silicon, which if the A series history is anything to go by, and it is, they will continue to do anyway. We’ll all reap the rewards, whichever platform we’re using.

I totally agree, there is no point ... the computing landscape I changing anyways, Apple is in the lead for Arm and others will follow (eg Qualcomm but others are rumored too), there is RSIC-V - that new landscape will stifle more competition and that is a good thing, for all of us.

 

[bill-p]

7zip is available on ARM MacOS. It's the defacto cross-platform standard that superceded rar and zip. Keka should be named Kaka.

https://sourceforge.net/p/sevenzip/discussion/45797/thread/ba29828ce0/

Well, of course there is a version that can be compiled on Mac. I meant there is no official GUI for 7-zip under Mac like there is for Windows like what was shown in that video. The GUI is the thing that contains the benchmark.

 

[mi7chy]

Well, of course there is a version that can be compiled on Mac. I meant there is no official GUI for 7-zip under Mac like there is for Windows like what was shown in that video. The GUI is the thing that contains the benchmark.

It's ARM command-line executable and has benchmark built-in.

 

[bill-p]

It's ARM command-line executable and has benchmark built-in.

Sure, okay, I'll give you that. But this video did not test that. They were clearly running 7-zip 19.0 under Parallels. 19.0 needs to run through emulation.

 

[nquinn]

I don't know about Matlab, but Excel? It may be ARM native, but it's notoriously much slower on intel macOS than on Windows.

Excel has always sucked horribly on macs

 

[Shirasaki]

Normal people on Mac don't run Matlab... nor do they run 7zip. Heck, 7zip doesn't even exist on Mac. We have Keka. Just the fact that you mentioned 7zip is already a signal to me that you don't use a Mac computer on a regular basis (or at all).

Also Mac doesn't need to export PDF files. The option to print and save as PDF has always been there and is much faster than some built-in PDF engines in some apps.

Some of the software shown are either being optimized for M1 or already has an alternative. The person doing the benchmark was just treating the MacBook as if it was a Windows machine going through Parallels. That's not realistic at all. Most Mac users just use MacOS.

Please get to know the target platform before you criticize it.

The only thing I want to say is: just because some Mac users don’t use those “pristine” macOS “optimised” applications, doesn’t automatically invalidate those users experience on macOS, just that they don’t bother spending much time finding “perfect” workflow that many die hard macOS fan does.

I use macOS and windows, so 7-zip is a well known app for me, even though I mainly use unarchiver on Mac. Same for Adobe acrobat, where it has all the features I need on both platforms. If you want to invalidate my experience on macOS just because I have no idea about applications you mentioned earlier, I’m fine with that, but some may not.

 

[Analog Kid]

I don’t mind giving hwub clicks honestly. They’re up there in pc hardware reviews with Gamers Nexus.

And that's where the disservice of this video comes back to the discussion. Viewing them through the lens of this video, they look just as ad-hoc and sensationalist as the rest of YouTube.

Sure, okay, I'll give you that. But this video did not test that. They were clearly running 7-zip 19.0 under Parallels. 19.0 needs to run through emulation.

So there's an ARM native build, but they didn't use that. They didn't use Rosetta. They ran an x86 binary inside x86 Windows inside a Parallels virtual environment competing with the native OS for resources? Was Windows Update running at the same time? I think that would "arguably be a more real world test" in this configuration...

 

[Analog Kid]

The only thing I want to say is: just because some Mac users don’t use those “pristine” macOS “optimised” applications, doesn’t automatically invalidate those users experience on macOS, just that they don’t bother spending much time finding “perfect” workflow that many die hard macOS fan does.

I use macOS and windows, so 7-zip is a well known app for me, even though I mainly use unarchiver on Mac. Same for Adobe acrobat, where it has all the features I need on both platforms. If you want to invalidate my experience on macOS just because I have no idea about applications you mentioned earlier, I’m fine with that, but some may not.

That was my point above-- this isn't an "arguably more real world test" as you've framed it. This is just saying that if you move your Windows workflow to an Apple MBP, you lose next to nothing while you transition to better optimized applications.

That, I believe, is a huge endorsement of Apple Silicon.

 

[spiderman0616]

I’ve given up on the X86/64 comparisons now, there seems little logical reason to it anymore.

If we’re Apple users, and considering this is MacRumors I’d guess many of us are (though I do still have a WinTel rig as well), then it makes no difference what the other side of the fence does, we’re not going to get it. Apple have moved on, personally I think for the better in the long run.

The only benefit now to Intel, AMD, Qualcomm and even ARM making advances is that it pushes their competitors. I’m all for Intel making better, faster (and hopefully more energy efficient) chips. But only because it’ll keep the pressure on Apple to improve Apple Silicon, which if the A series history is anything to go by, and it is, they will continue to do anyway. We’ll all reap the rewards, whichever platform we’re using.

Agree. I'm not even nearly as long-suffering of a Mac user as some of you--I've only been using them since the early to mid 90s--but I am SO TIRED of them running slow, hot, and loud, and it does feel good to crow a little bit about Apple Silicon. I had really kind of given up on the idea of ever owning a MacBook of any kind again as long as they were going to continue to increase in heat output and power consumption.

The M1 MacBook Air I'm typing on now, even a year later, feels like a huge leapfrog product to me. Not only over my 2019 Intel MacBook Pro, but also over the 12.9" iPad Pro that my MacBook Air replaced. I lost the Pencil and touchscreen support, but I gained hours and hours of battery, excellent portability without the thick and heavy keyboard add-on, and a CPU that handles my amateur photo and video editing better than any device I've ever owned.

I really and truly believe we are seeing a rarity right now: disruption in absolute plain sight. Usually you don't know it was a disruption until later. I think the ORIGINAL three M1 Macs were a disruption. I know many pundits and reviewers thought Apple would botch either the software transition or the hardware transition and that M1 was just their prototype for their "cheap" computers. They did not expect Apple to more or less nail it on the first try and then re-impress us 10x over the next year with the Pro and Max upgrades that aren't even being marketed as a new chip architecture yet.

I think people are being pretty smug about all this right now, because for so long they couldn't be. Apple outgrew Intel so long ago, and only Apple seemed to recognize that it was a dead end path back then. If anyone else had the same thought, Intel wouldn't be fighting so hard for attention in their marketing right now.

 

[bill-p]

The only thing I want to say is: just because some Mac users don’t use those “pristine” macOS “optimised” applications, doesn’t automatically invalidate those users experience on macOS, just that they don’t bother spending much time finding “perfect” workflow that many die hard macOS fan does.

I use macOS and windows, so 7-zip is a well known app for me, even though I mainly use unarchiver on Mac. Same for Adobe acrobat, where it has all the features I need on both platforms. If you want to invalidate my experience on macOS just because I have no idea about applications you mentioned earlier, I’m fine with that, but some may not.

Well, just because you found some benchmarks where the M1 Pro/Max chips are not able to maximize performance doesn't mean they are not amazing overall. Even the video you shared to us concluded as much.

I'm not invalidating your experience on MacOS, but I'm seriously questioning your motive by posting this video without any context. You clearly don't seem to understand why those numbers are the way they are, or why the video's conclusion is against your own.

 

[bill-p]

So there's an ARM native build, but they didn't use that. They didn't use Rosetta. They ran an x86 binary inside x86 Windows inside a Parallels virtual environment competing with the native OS for resources? Was Windows Update running at the same time? I think that would "arguably be a more real world test" in this configuration...

No, they likely ran an x86-64 binary (I'm guessing?) inside ARM64 Windows inside Parallels (x86 Windows can't run under Parallels yet). There is an x86-64 emulation layer written for Windows on ARM by Microsoft in order to improve compatibility. That's why Windows on ARM can be ran via Parallels and can run a number of x86 applications.

I am guessing that is the case? Because otherwise they have to deal with different versions of the same app. In the case of 7-zip, there is a command-line tool and perhaps you can benchmark it that way but it's much less visual than the Windows version.

So this is probably "arguably a real world test for people wanting to run Windows on M1", but it's not very representative of a MacOS workflow.