Earlier today, Adobe finally released the full non-beta version of Photoshop for Apple Silicon, and we had a chance to try it out. I have no qualms: the benchmarks are really impressive, matching or surpassing Intel-based computers that cost two to three times more.
We had been waiting for this release for some time, playing with the Beta version of Photoshop for Apple Silicon and crossing our fingers so that the final version would take full advantage of the M1’s impressive performance, unlike the Lightroom CC. Now we have our answer, and it is even better for photographers and photo editing than we might expect.
How we test performance
When testing Photoshop performance in our reviews here at PetaPixel, we used the PugetBench Beta v0.8 benchmark from Puget Systems. Why the older beta? Because it is the latest version that included the Photo Merge test: a data point that is exclusively important for photographers, but very painful for Puget to include in the latest versions of the benchmark. As you will soon see, it is a good thing to keep this old benchmark for testing, because Photo Merge is the superpower of the M1.
In the graphics below, you will see four computers listed: M1 Mac mini (Apple Silicon), M1 Mac mini (Rosetta 2), 13-inch MacBook Pro and Dell XPS 17. The idea was to show how the Photoshop x86 works on Intel Hardware (MBP 13-inch and XPS 17), via Rosetta 2 emulation on the M1 Mac mini, and then compare those three scores with the version optimized for Apple Silicon running on the same Mac mini.
Keep in mind that both the 13-inch MacBook Pro and the Dell XPS 17 have 32 GB of total RAM versus the 16 GB of the Mac mini. The XPS 17 is also running a 10th generation Intel Core i9-10875H 8-core alongside a GeForce RTX 2060 Max-Q GPU with 6 GB of VRAM. Finally, both the 13-inch Intel MacBook Pro ($ 3,000) and the Dell XPS 17 ($ 3,000) that we tested cost much more than the fully loaded M1 Mac mini ($ 1,700) used for this comparison.
And still…
Results: Apple Silicon vs Rosetta 2 vs Intel
Unsurprisingly, the M1 Mac mini loses to the competition in the raw performance of the GPU, more or less matching the integrated graphics of the Core i7 quad-core that is in the 13-inch MacBook Pro (full review here). But even with that score working against it, the Mac mini running Photoshop optimized for Apple Silicon managed to get the second highest overall score we’ve ever seen on PugetBench.
What’s more, none of the computers we tested, not even the most expensive 16-inch MacBook Pro you can buy or the Razer Blade Studio Edition, ever surpassed the 100 mark in the PugetBench Photo Merge test. Running Photoshop optimized, the M1 Mac mini reached 130+ race after race after race.
What does this mean in real terms? An Intel-based 13-inch MacBook Pro with a 2.3 GHz i7 quad-core and 32 GB of RAM takes about 2 minutes and 45 seconds to merge a panoramic photo of 6 photos on the Nikon D850 (full resolution .NEF Raw files). The Mac mini M1 running Photoshop optimized does the same task in 1 minute and 14 seconds. Even a $ 6,700 16-inch MacBook Pro fully loaded with an 8-core Intel Core i9 and discrete GPU takes 1 minute 52 seconds.
All this from a chip that consumes energy so slowly that we were able to get almost 16 hours of 4K video playback with the M1 MacBook Pro that we reviewed in December.
Final thoughts: What does this mean for creatives?
After the lackluster improvements we saw when we compared the Lightroom optimized with Apple’s Silicon with the x86 version running via Rosetta 2, we did not enter this test with high hopes. Seeing the score so much, when Rosetta 2 was already doing a great job with the x86 version of Photoshop, it was frankly mind-blowing. I thought the first race was a mistake; on the 6th I was forced to start believing in my eyes.
As a reviewer, you are always concerned that you have sold something that really impressed you. I said that the M1 MacBook Pro “changes everything” and called the M1 Mac mini “the best Mac for most photographers” and, although I was quite confident, sarcastic comments make you doubt your own sanity. Benchmarks like this help to prove that none of these claims is as hyperbolic as it might first appear.
When companies like Adobe make the most of what Apple created on the M1, the results are undeniable.
It remains to be seen how Intel, AMD and the PC market in general will decide to respond. Will ARM-based PCs take off now that more and more software companies are taking the time to optimize their applications for Apple Silicon, or are AMD’s latest Ryzen processors efficient yet powerful enough to keep creators from leaving the boat? And how can Intel wage war on two fronts, with AMD destroying it on the x86 and Apple exploding on the ARM?
Whether you love or hate Apple, this is irrelevant. It is not about Apple Silicon vs Intel vs AMD and whether you are a Mac or a PC. What is happening here is a rekindling of the competition. And when companies compete, customers win.