'M2 Max' Geekbench Scores Leak Online, Revealing Rumored Specs and Performance

There was some speculation on these forums that Apple showed a prototype of the Apple silicon Mac Pro to some of their target market and got a negative response. Hence we are still waiting for an ASi Mac Pro because no one would buy one as designed. I have no idea if that speculation is correct but it would explain the delay.

They don't have any hardware yet to be used in a Mac Pro. Were these speculations based on industry rumours or some other information, or just people thinking out loud?
 
They don't have any hardware yet to be used in a Mac Pro. Were these speculations based on industry rumours or some other information, or just people thinking out loud?
It was claimed to be industry insiders but who knows. I just thought it was interesting speculation that fits the current missed two year timeline.

Edit: Sorry, I misremembered the thread. It was pure speculation based on what Apple did with the 2013 Mac Pro. The post I remembered is here.
 
Last edited:
It's the only argument. We are talking about the likelihood of shipping feature X.

What was the likelihood of doing their own CPU architecture, ca. 2006?

What was the likelihood of moving the Mac to it?




I believe it will have UMA and integrated memory only, and that it will have PCIe slots but not for GPUs. I also believe that in order to be a successful product it would either need to use an SoC that is so much faster than anything else that third-party GPUs would become pointless in principle; or, use a modular NUMA architecture where you can use multiple compute boards (each with their own SoC/CPU/GPU/integrated RAM) + shared extendable RAM. But that's a whole other can of worms and it's not clear to me that Apple will go there.


Either way, they will do just fine even without a Mac Pro. Maybe we will see Apple abandon the high-end desktop market altogether. Who knows.

They've already announced they're doing a Mac Pro, and doing a Mac Pro that doesn't have support for additional memory nor additional GPUs sounds like they might as well not do the product.

Also, compute boards? That sounds way more complicated than just doing the obvious thing, which is to add support for third-party GPUs.
 
What was the likelihood of doing their own CPU architecture, ca. 2006?

I think we were talking about next year, not 15 years in the future? In 15 years there might be no dGPUs at all 😉

Anyway, we will have to wait and see. Right now we are operating on gut feeling and what we consider "sensible". I don't think there is much to add in the ways of speculation. We can reevaluate our beliefs when the products are out. Not that I have a good track record predicting where Apple will go next :D
 
2 more cores and only 10% speed bump? That doesn't seem right.
2 more cores + m2 architecture boost should net at least 25% speed bump.

M2 Air is 20% better on multicore than M1 Air, and it has the same core count.
 
That's a pathetic 11% increase only, after more than a year release cycle. This is a worse increment than intel-macs upgrades. At least those were upgraded by more than 15%, as far as I remember.
I don’t think I’ll ever be able to understand this frame of reference.

Why is everyone chasing more and more power? Why did we stop buying computers to make them last? Why is the market and community focused on major yearly increments?

Do you all genuinely buy new computers every year? I didn’t update the CPU or GPU in my personal built desktop for 5 years. I get constantly replacing the phones because they (usually) make much more changes than just the chip, but the computer?

What am I missing? Why is incremental now bad?
 
I don’t think I’ll ever be able to understand this frame of reference.

Why is everyone chasing more and more power? Why did we stop buying computers to make them last? Why is the market and community focused on major yearly increments?

Do you all genuinely buy new computers every year? I didn’t update the CPU or GPU in my personal built desktop for 5 years. I get constantly replacing the phones because they (usually) make much more changes than just the chip, but the computer?

What am I missing? Why is incremental now bad?
Well for me personally:
- i was hoping for more because M1 to M2 Air upgrade showed 20% bump on the same core count
- i'm generally waiting for Thunderbolt5, and i'm sticking to the M1 13" till i can, it's becoming stuffy (Great, but stuffy)
- i was considering waiting for M2 Pro chips based on the M1 to M2 performance bump, and this is rather disappointing. Two more cores = more heat for less of a performance bump than architecture alone did on M2 Air? it doesn't sound right honestly.
 
I don’t think I’ll ever be able to understand this frame of reference.

Why is everyone chasing more and more power? Why did we stop buying computers to make them last? Why is the market and community focused on major yearly increments?

Do you all genuinely buy new computers every year? I didn’t update the CPU or GPU in my personal built desktop for 5 years. I get constantly replacing the phones because they (usually) make much more changes than just the chip, but the computer?

What am I missing? Why is incremental now bad?

Yes, you are correct about a few things.

Making computers last or any device for that matter obviously takes the prime spot, no doubt and so MacBooks 2016 ~ 2019 (pre-16inch) were horrible, not built to last and performance was bad too.

Intel Macs faced a few challenges, severe heat, and severe throttling. I had a Late 2013 MBP 15-inch and the performance was adequate to my needs but would throttle down by 300%, from 3.4GHz to 700MHz, even moving a window was stuttery.

Then they shifted the entire architecture to solve those issues. Imagine, every app being re-compiled for it. Imagine from a user's perspective, trusting and following Apple on this wild ride to glory that could take years. Less heat, more power and no throttling. Did they achieve that? Hell yes!

Now the question is will they be able to sustain it? The answer to that question is what all this discussion is about. If they are hitting a wall in performance and power now in just 2nd gen, once I'm ready to upgrade my MBP after 5-6years will I get something that is outdated compared to what I could've got if Apple stayed with Intel/AMD?
 
2 more cores and only 10% speed bump? That doesn't seem right.
2 more cores + m2 architecture boost should net at least 25% speed bump.

M2 Air is 20% better on multicore than M1 Air, and it has the same core count.

It's two more efficiency cores. The IPC of the big cores is the same, so what you are looking at is mostly a higher frequency.
 
I don’t think I’ll ever be able to understand this frame of reference.

Why is everyone chasing more and more power? Why did we stop buying computers to make them last? Why is the market and community focused on major yearly increments?

Do you all genuinely buy new computers every year? I didn’t update the CPU or GPU in my personal built desktop for 5 years. I get constantly replacing the phones because they (usually) make much more changes than just the chip, but the computer?

What am I missing? Why is incremental now bad?

What exactly do you mean by "making computers last"? Computer performance is a limiting factor for many professionals. When I run a statistical model or re-export part of our databases, any downtime directly negatively affects my productivity. Same for building software, doing media creation or editing etc. or any kind of workflow where you iterate, inspect the result and iterate again. It can be as simple as waiting for a LaTeX paper to compile or a research poster to export from the editing software. I have to fix the typos/layout issues and then rebuild the document again. These minutes of waiting between takes really make a huge practical difference. Already the M1 machines have boosted my productivity tremendously because my laptop now can apply complex data transformations and dump the data for inspection as quickly as I switch between the code editor and the file browser. So I have continuous feedback and can check the output of my code immediately.

Of course, none of this matters to an average office or email user who just uses the computer for organising. But still, we have new applications and methods (ML) which require more performance and more capability. It's important to have steady progress. I think what people worry about is Apple chips stagnating like what we had with Intel post 2014...
 
Hmm… what if Apple is still developing macOS 13.2… this score is 1000 points higher so there is a chance that apple needs to optimize the software.
 
Hmm… what if Apple is still developing macOS 13.2… this score is 1000 points higher so there is a chance that apple needs to optimize the software.
Maybe the bump is cause the M2 Pro and Max are running at higher clocks than the regular M2 and the prior runs.
 
It's two more efficiency cores. The IPC of the big cores is the same, so what you are looking at is mostly a higher frequency.
Oh. That makes more sense.
Also, too bad.

No, this bump is in line with what the M1/M2 bump did.
yeah,i wasn't aware two more cores are efficiency cores.


On that note, i would really appreciate if people stop referring to AS chips as "8, 10, 12, 20-core". efficiency cores on 4/4 give about 30%, on 8/2 more akin to 10%.

there's two 8-cores to begin with, the M1 Pro 6/2 and M1/M2 4/4.

Just say 8/4 core for the 12.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Back
Top