Earlier quoted context omitted.
[flagged]
[flagged]
are you comparing the same models? How did you calculate the TOPS for M3 Ultra?
Apple M3 Ultra
871–880 of 1001 posts
Re: Apple M3 Ultra
#872They are going to have more memory than storage at this rate.
Re: Apple M3 Ultra
#873Earlier quoted context omitted.
It's new for mainstream PCs to have it.
Nope, it was common in 8 and 16 bit home computers, and in respect to PCs themselves graphics memory was mapped into the main memory until the arrival of 3D dedicated cards. And even with 3D, integrated GPUs have existed for years.
Like pretty much every game console.
Re: Apple M3 Ultra
#874Re: Apple M3 Ultra
#875Whoa. M3 instead of M4. I wonder if this was basically binning, but I thought that I had read somewhere that the interposer that enabled this for the M1 chips where not available. That Said, 512GB of unified ram with access to the NPU is absolutely a game changer. My guess is that Apple developed this chip for their internal AI efforts, and are now at the point where they are releasing it publicly for others to use.…
If Apple supported Linux (headless) natively, and we could rack m4 pros, I absolutely would use them in our Colo. The CPUs have zero competition in terms of speed, memory bandwidth. Still blown away no other company has been able to produce Arm server chips that can compete.
Is it impossible to use macOS as a virtualization host?
Re: Apple M3 Ultra
#876Surprised they didn't do an M4 Ultra. I really hope they don't do an M4 Ultra for the Mac Pro and add in this very undesirable kind of product matrix just for the sake of differentiation. I would be ok with an M3 Extreme in the Mac Pro, however.
Re: Apple M3 Ultra
#877Earlier quoted context omitted.
No, because there is no CUDA. We have fast and cheap alternatives to NVIDIA, but they do not have CUDA. This is why NVIDIA has 90% margins on its hardware.
CUDA is simply not important for modern vLLM and many many others. DeepSeek V3 works great on SGLang. https://www.amd.com/en/developer/resources/technical-article... Can you do absolutely everything? No. But most models will run or retrain fine now without CUDA. This premise keeps getting recycled from the past, even as that past has grown ever more distant.
CUDA is incredibly important still. It's still an incredible amount of work to get packages working on multiple GPU paradigms, and by default everyone still starts with CUDA.
The example I always give is FFT libraries - if you compare cuFFT to rocFFT. rocFFT only just released support for distributed transforms in December 2024, something you've been able to do since CUDA Toolkit v8.0, released in 2017. It's like this across the whole AMD toolkit, they're so far behind CUDA it's kind of laughable.
Re: Apple M3 Ultra
#878Earlier quoted context omitted.
That’s what’s weird to me too. It’s not like they would lose sales of macOS as it is given away with the hardware. So if someone wants to buy Apple hardware to run Linux, it does not have a negative affect to AAPL
Except the linux users won't be buying Apple software, from the app store or elsewhere. They won't subscribe to iCloud.
You also lose out on developers. The more macOS users, the more attractive it is to develop for. Supporting Linux would be a loss for the macOS ecosystem, and we all know what that leads to.
Re: Apple M3 Ultra
#879Earlier quoted context omitted.
We finally encountered the situation where an Apple computer is cheaper than its competition ;-) All joking aside, I don't think Apples are that expensive compared to similar high-end gear. I don't think there is any other compact desktop computer with half a terabyte of RAM accessible to the GPU.
And yet all that cash still just goes to TSMC
They are selling the shovels for this gold rush. Also, ASML, who sells machines to make shovels.