Mine works without issue, so perhaps it’s “iffy” as you say… 🤷
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
M2 Ultra Chip Benchmark Results Reveal Impressive Performance Gains
- Thread starter MacRumors
- Start date
- Sort by reaction score
I bet the intel mac pro with graphics upgrades would destroy the M2 series studio. That stat is conveniently left out of their marketing.
I was more pointing in the direction that the argument "the hardware is not good enough for gaming because it's not as fast as a dedicated high end GPU" is a little bit lacking, considering the fact that a lot hardware that is used for gaming, even state of the art big titles, is less capable than the M2. For some reason that often gets mixed together with other topics and by the numbers you can see how incredibly niche that market / target group in gaming is.
However most people in the forums that are upset about the Apple Silicon Mac Pro not supporting dedicated GPUs via PCI want to use it for other stuff than gaming, for example 3D rendering or machine learning. I have no idea how big that group is and wether Apple just tends to ignore it or if they didn't get as far with the Silicon Mac Pro development as they originally intended and had to release a compromise.
The first benchmark results for Apple's new M2 Ultra chip have surfaced on Geekbench 6, providing a closer look at CPU performance improvements. The high-end chip is available in the new Mac Studio and Mac Pro models launching next week.
There is currently some variance in the results, but the Mac Studio with the M2 Ultra chip appears to have single-core and multi-core scores of up to approximately 2,800 and 21,700, respectively. As expected, these scores confirm that the M2 Ultra chip offers up to 20% faster CPU performance compared to the M1 Ultra chip, as Apple advertised. This also means the M2 Ultra is now the fastest chip that Apple has ever released.
Geekbench 6 result for Mac Studio with M2 Ultra chip
More interestingly, the scores reveal that the new Mac Pro should have around 2× faster overall CPU performance than the fastest Intel-based Mac Pro with a 28-core Xeon W processor. This feat is even more impressive given that the new Mac Pro starts at $6,999, while the 28-core Intel-based model started at $12,999, nearly double the price. During its WWDC keynote, Apple said the new Mac Pro is up to 3× faster than the Intel-based model, but that only applies to select "real-world pro workflows like video transcoding and 3D simulation."
The primary reason to consider the Mac Pro over the Mac Studio is for the desktop tower's six available PCIe expansion slots. Otherwise, customers should consider the Mac Studio, as it can be configured with the M2 Ultra for $3,000 less than the Mac Pro. For a more detailed comparison, read our Mac Studio vs. Mac Pro Buyer's Guide.
The new Mac Studio and Mac Pro are available to order now, and will begin arriving to customers and launch in stores on Tuesday, June 13.
Article Link: M2 Ultra Chip Benchmark Results Reveal Impressive Performance Gains
Well Apple you have one very irked customer -- 07 April 2022 I received my Mac Studio Ultra - order placed the same day it was launched - and barely 14 months later we have a NEW version - better, faster and guess what the same fricking price. If I was not super happy with the M1 ultra studio I have I would have been more than a little irked.
What happened to the 2-3 year product update cycle -- now wait a week and what ever you bought is "out of date".
WHY are you stuck on 8TB Apple -- come on -- where are the 16, 24, 32 TB options?
It really makes me wonder about the updated MacPro -- where is the program to take old intel "new" mac pros and update their motherboards and chips. I still own a trashcan it is just getting dusty these days.
As t the stupid vision -- if there ever was a toy designed to relieve the sill people of their pocket money this is it.
Last edited:
These are not PC users who want to run MacOS though. These are Mac/Apple users who want to run MacOS on PC hardware. The difference is not that subtle. I have never seen the discussion of how to run MacOS on PC forums. These discussions typically happen on Apple related forums. People understandably want to avoid Apple tax.
Yes, in fact the first RTX 4000 cards on Steam are 4070 Ti with 0.46% market share at place 46 and 4090 with 0.44% at place 47.
I just waded through all >250 comments (don't ask why, probably brain damage). I am amazed that nobody has pointed out the one really interesting thing coming out of these benchmark numbers.
I mean, we all get that M2 Ultra CPU single- and multi-core have improved on the order of 15-20%. Totally expected, a continuation of the M2 story: Apple got stuck on the N5/N4 process, not only losing the advantage of a new process node, but also having to shelve their new designs, which couldn't be backported. As an almost-last-minute fallback position, the M2 was a good save but not the chip anyone wanted.
...but wait.
The M2 Ultra's "compute" numbers (ie, GPU) are NOT as expected. I'm not comparing to nVidia or AMD - I've no intention of wading into that morass. I'm just talking about the change from the M1 Ultra, or from the M2 Max.
Here's the M1 Max/Ultra and M2 Max/Ultra numbers. Note that these are not perfectly reliable as GeekBench numbers tend to vary a lot between reporters, probably due to a lot of people having no clue how to run benchmarks. And since they don't provide an average for this number (as opposed to the single/multicore), I'm just eyeballing the highest substantial cluster within recent results
M1Max: ~119k
M1Ultra: ~175k (very few outliers in 180+)
M2Max: ~138k
M2Ultra: ~223k
So... The M1 Ultra, as we already knew, scaled very poorly. ~47% higher score with 100% more GPU cores.
The M2 Max GPU score is roughly 15% higher than the M1 Max. But what about the M2 Ultra? It's 27% higher than the M1 Ultra and 61% higher than the M2 Max. That's a substantial improvement in scaling. It's *still* pretty poor, but notably better. (We also have very few scores for the Ultra so far; it's possible the numbers will change as more results come in.)
This is one of very few things in the M2 line that are outside the envelope of the 15-20% bump that comes mostly from clocks.
[Edit: added a comparison M1/M2 Ultra, accidentally left that out]
I mean, we all get that M2 Ultra CPU single- and multi-core have improved on the order of 15-20%. Totally expected, a continuation of the M2 story: Apple got stuck on the N5/N4 process, not only losing the advantage of a new process node, but also having to shelve their new designs, which couldn't be backported. As an almost-last-minute fallback position, the M2 was a good save but not the chip anyone wanted.
...but wait.
The M2 Ultra's "compute" numbers (ie, GPU) are NOT as expected. I'm not comparing to nVidia or AMD - I've no intention of wading into that morass. I'm just talking about the change from the M1 Ultra, or from the M2 Max.
Here's the M1 Max/Ultra and M2 Max/Ultra numbers. Note that these are not perfectly reliable as GeekBench numbers tend to vary a lot between reporters, probably due to a lot of people having no clue how to run benchmarks. And since they don't provide an average for this number (as opposed to the single/multicore), I'm just eyeballing the highest substantial cluster within recent results
M1Max: ~119k
M1Ultra: ~175k (very few outliers in 180+)
M2Max: ~138k
M2Ultra: ~223k
So... The M1 Ultra, as we already knew, scaled very poorly. ~47% higher score with 100% more GPU cores.
The M2 Max GPU score is roughly 15% higher than the M1 Max. But what about the M2 Ultra? It's 27% higher than the M1 Ultra and 61% higher than the M2 Max. That's a substantial improvement in scaling. It's *still* pretty poor, but notably better. (We also have very few scores for the Ultra so far; it's possible the numbers will change as more results come in.)
This is one of very few things in the M2 line that are outside the envelope of the 15-20% bump that comes mostly from clocks.
[Edit: added a comparison M1/M2 Ultra, accidentally left that out]
Last edited:
I thought the fans in the Mac Pro and the Mac Studio constantly spin… ?
I completely agree. The Mac Pro doesn’t seem well thought out. No pcie 5. No upgradable ram. No pcie gpu. No standard nvme slots. I doubt m2 ultra will run at any higher clock speeds in the Mac Pro than the Mac Studio.
Yay, its faster than a MacOS system based on a high-end 2019 intel-CPU. But time has passed ...
It’s also just as rare for Apple to announce a product more than 6 months away from being able to sell it.
Not only that, people want to be able to upgrade when they see fit. If I want to buy a system with 16gb of ram, and then later add more, I should be able to. I should not have to shell out 3x the regular cost of a drive just to upgrade it at POS with apple (or any manufacturer). I purchase all my computers with upgradability. That way I can do it when I want.
Who needs CPU anyway? cpu's are fast enough the last 5 years. We need fast gpu's! wonder how they compare to nvidia! don't think the top gpu's would be faster than a 2080ti.
Yes, however, how much difference will you see from one year old cpu compared to current? 2 to 3 percent imo in real wold use.
Oh...somewhat on topic, Thank you to all the apple crowd here for being mature and having a great conversation about all this stuff! I applaud you all! Run whatcha brung!
I generally strongly recommend people don't buy a year-over-year upgrade, so I don't really care about the answer to that question.
A14 to A15 isn't a huge bump, but that's OK as long as they still average a double-figure percentage yoy.
That's exactly my point. There is not that much difference YOY for CPU/GPU speed / productivity increases. The delta starts at about the 5 year mark where and older system will be "noticeably" slower. Even then, you would probably have to time it or have it side by side to notice.
yes but not everyone who buys games is a hardcore gamer … it will need to be a critical mass of more than casual and less than hardcore gamers 😉
Forgive me if this has been discussed before. Does anyone know how the Mx SoCs handle things if one of more parts on the chip fail? For example, let's say that two of the GPU cores fail and maybe a bank of RAM. Does the SoC dynamically switch off those portions so the rest function as normal, or is the whole chip toast at this point?