Real world experience with the new M1 Macs have started trickling in. They are fast. Very, very fast. Developer Erik Engheim explains why.
On Youtube I watched a Mac user who had bought an iMac last year. It was maxed out with 40 GB of RAM costing him about $4000. He watched in disbelief how his hyper expensive iMac was being demolished by his new M1 Mac Mini, which he had paid a measly $700 for.
We couldn’t find the exact video (let us know below if you have the link), but here’s the M1 Mac Mini vs. an 8-core 2020 iMac 5K with 64GB RAM and a 5500XT GPU:
In real world test after test, the M1 Macs are not merely inching past top of the line Intel Macs, they are destroying them. In disbelief people have started asking how on earth this is possible?
If you are one of those people, you have come to the right place…
Fortunately for AMD and Intel, Apple doesn’t sell their chips on the market. So PC users will simply have to put up with whatever they are offering. PC users may jump ship, but that is a slow process. You don’t leave immediately a platform you are heavily invested in.
But young professionals, with money to burn without too deep investments in any platform, may increasingly turn to Apple in the future, beefing up their hold on the premium market and consequently their share of the total profit in the PC market.
MacDailyNews Take: Great sales pitch for x86 PCs: Just put up with totally outmoded performance. That’ll work wonders!
Read the full article which explains nicely why Apple’s M1 chip is so fast.
Buh-bye, Intel slug! Intel served its purpose, but has been a boat anchor for years. Hello, Apple-designed ARM-based Macs! — MacDailyNews, April 23, 2020
Yes, the slowness and reluctance of Intel’s CPU development astounds and boggles.
Did they put a marketing-type in charge? 🙂
Probably a beancounter…
What would this more efficient performance per watt mean for super computers? I soooo hope Apple builds a super computer out of M1’s (or possibly the M1Xs that are coming).
World’s Fastest Supercomputer Fugaku uses ARM cores.
Really informative article.
First good comment applecynic has said in years. Maybe the only good one I’ve ever read.
Oh well, a broken clock is still right twice a day, for a minute at a time.
Probably one of those brief windows for Applesooknic.
Not true. Although a well deserved Apple critic at times certainly he has many posts enlightening and spot on. Politics he is a tool but listens, half joking AC… 😉
This is a good thing for the industry. I think you’ll see PC manufacturers jump on the ARM bandwagon sooner rather than later. I KNOW that Windows has an ARM version of Windows available.
These aren’t ARM chips. Apple Silicon incorporates over a decade of proprietary development. The PC guys can’t just swap ARM for x86 and match M1 performance.
My goodness, TXUser right for once too.
True. But will PC manufacturers and buyers understand that? They might jump on the ARM bandwagon anyway and be disappointed that they aren’t getting Apple performance.
IMO unlikely. It would lead to Nvidia vs Intel vs AMD (etc.) competing to create the SoC instead of each specializing in their respective areas of expertise. The more likely scenario is that PC and Mac will evolve in different directions for different needs. As technologies improve it may lead to innovations for the bottlenecks in the modularity of the PC model.
Nvidia and AMD can possibly, and without too much effort, exceed it. The main speed gains are in memory access due to SoC. Also, these are mobile chips within a mobile power envelope. Desktops are far less restricted.
Great article. Seems the M1 is just the opening salvo.
“Can’t innovate anymore? My ass!” Phil Schiller.
As he introduced the late 2013 Mac Pro…how did that work out?
Definitely an interesting article. I found however the lack of discussion about the layer that Windows abstracts between the OS and the HW to allow Windows to run virtually unchanged across processor platforms as another source of ‘degraded’ performance disappointing. As evidenced in iOS vs Android, that virtualizing layer does make for a significant portion of the speed difference in exchange for the flexibility of running on a much larger variety of processors that Windows and Android have chosen.
I doubt that the PC world (or Android for that matter) will change course in the future regarding continued use of a virtualization layer. Whether that is a benefit or detriment will work itself out.
Think I’ve heard that song before…
and played by Apple last time too.
EDIT: keep on forgetting that MDN doesn’t allow URLs…
Find the youtube video … “Apple Launches New “Snail” Commercial”
The difference here is that Motorola and IBM got greedy, and neglected Apple when they thought the world was at their feet. Apple is not going to do that to themselves.
True, there were reasons for why the PPC architecture floundered, but by the same token, there was also more resources for development. Same also applies for Intel because of the breadth & width of their customer base.
My big concern with Apple and the M1 isn’t this generation, but 2-3-4 generations down the road, for its likely that most of the gains have already been consumed in developing the M1. Not a unique or unusual problem…
The price comparison between the M1 and iMac is not strictly fair. I’ve been trying to decide which of those two to get to replace a machine that just died, and a comparably-configured iMac comes out significantly lower on price. An M1 with 16GB, 1 TB drive, keyboard, mouse, and 5K display comes in around $2800. A 6-core 27″ iMac with the same RAM and storage is $2430. If you do your own upgrades, the iMac is even less. All things being equal, an iMac will save you about $400 over an M1 Mac. The M1 clearly outperforms the iMac, but it’s misleading to suggest that the M1 is less expensive.
The M1 Mac Mini is only more expensive if you need 16GB of memory, which the reviewers say most users who deal with individual files smaller than 8GB don’t, and can use a Thunderbolt 3 external drive on your desk for most of your data.
I’ve got 24 GB in my iMac now, so going down to 16 with no upgrade path seems iffy to me. On the other hand, I see quite a bit of value in being able to plug other things besides my mac into a monitor. I wish iMacs had HDMI input.
This is what I’ve been concerned about as well: an 8GB machine may be perfectly fine for the generic “Facebook consumer” workflows, but when it gets into stuff with more heavy lifting, you want to at least have the option of throwing hardware at the problem, and in the current environment, more RAM is relatively cheap. As such, for as long as I/O to RAM is faster than SSD, there’s going to be a performance hit on workflows that benefit from more RAM than what Apple has decided to make available in their design.
Another factor: 4k monitors are FAR cheaper than 5k, and unless you edit lots of 4k video, they probably are just as good. You can get a 32″ one for $410.
4K displays are typically only 27″, though they are a lot cheaper. And substituting a disk for RAM would reduce the cost of the Mac, but wouldn’t have much effect on the total cost.
The Apple 1TB SSD upgrade is $400. There are external Thunderbolt 3 drives for under $300. If you can live with USB 3.1, you could cut that to under $100.
As for memory, the M1 uses a completely different memory model than the x86, so it does significantly less paging at 8 or 16GB.
People keep forgetting that an M1 Mac with less memory is worth the same as an Intel Mac with more memory – in fact, the M1 is way better
Wonderful specs but they do not run Windows 10. Not useful for serious work.
Probably don’t have a COBOL compiler, either.
Only morons use Windows. Thanks for making it clear never to take anything raucous rauckr says seriously, because if you use Windows, then it’s John McEnroe all the way – you cannot be serious.