M1 Ultra Outperforms 28-Core Intel Mac Pro in First Leaked Benchmark
The first benchmark for Apple's M1 Ultra chip popped up on Geekbench following today's event, confirming that the doubled-up M1 Max is indeed able to outperform the highest-end Mac Pro as Apple claims.
Labeled Mac13,2, the Mac Studio with 20-core M1 Ultra that was benchmarked earned a single-core score of 1793 and a multi-core score of 24055.
Comparatively, the highest-end Mac Pro with 28-core Intel Xeon W chip has a single-core score of 1152 and a multi-core score of 19951, so the M1 Ultra is 21 percent faster in this particular benchmark comparison when it comes to multi-core performance. As for single-core performance, the M1 Ultra is 56 percent faster than the 28-core Mac Pro.
Apple has claimed that the M1 Ultra is up to 60 percent faster than the 28-core Mac Pro when it comes to CPU performance, so Apple may be referencing single-core differences in the metrics that it shared during today's event. This is just one benchmark, so we could see the M1 Ultra performing better in additional benchmarks following the March 18 release of the Mac Studio.
Top Rated Comments
With the caveat that, yes, Geekbench is a synthetic benchmark, this thing appears to be significantly outperforming the top-of-line, just-launched 12th-gen i9 desktop parts. Given that the i9-12900K has a TDP of 125W and turbo power rating of 240W, and this thing fits in a compact desktop, I would be feeling more than a little nervous if I were Intel.
The M1 Ultra is even competitive with all but the most extreme big-iron many-core Xeon and Threadripper CPUs, and the entire computer costs less than many of those chips (its also probably smaller than the CPU cooler on some of them)... but it doesn't have 1TB+ of ECC RAM or some of the other features big-iron desktops have.
Which is why I'd be even more nervous, if I were Intel, that Apple hasn't put their own silicon in the Mac Pro yet. That's a pretty strong indication that Apple has something even-higher-end in the pipeline.
Apps I use max out the GPU. The more I add into the 3D model the more RAM it uses plus FPS drop [geometry and textures]. This is gaming engine software.
My 3080ti is already maxed in RAM on my PC, and I am totally over the heat and noise from it.
It simply is insane what apps can use these days in terms of resources and power, and personally I never want my computer to restrict my work in any way.
We get paid a lot of money to be able to deliver good quality design work, quickly. This machine is still actually less than the app subscriptions used on it, believe it or not.
I actually believe the studio is well priced for what it delivers [or at least what I expect it to].
Edit: and almost as fast as the 64-core AMD Ryzen Threadripper 3990X which scores about 25000.