I would want to know if the LPDDR6 rumors are substantiated, i.e. memory bus details. https://forums.macrumors.com/threads/lpddr6-new-beginning-of... If M4 Max could finally break the 400GBps limit of the past few years and hit 600 GBps, it would be huge for local AI since it could directly translate into inference speedups.
The M4 has increased the bandwidth from 100 to 120 GB/s. The M4 Max would probably be 4x that at 480 GB/s, but the M4 Ultra would be 960 GB/s compared to M2 Ultra at 800 GB/s.
Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
> This is completely coherent with their privacy-first strategy How can they have a privacy first strategy when they operate an Ad network and have their Chinese data centers run by state controlled companies?
... I think that the more correct assertion would be that Apple is a sector leader in privacy. If only because their competitors make no bones about violating the privacy of their customers as it is the basis of thier business model. So it's not that Apple is A+ so much as the other students are getting Ds and Fs.
> This is completely coherent with their privacy-first strategy (which would be at odds with sending data up to the cloud for processing). I feel like people are being a bit naïve here. Apple's "Privacy First" strategy was a marketing spin developed in response to being dead-last in web-development/cloud computing/smart features. Apple has had no problem changing their standards by 180 degrees and being blatantly ant…
Don't bother the fanboys have an Apple can't do anything wrong/malicious. At this point it's closer to a religion than ever. You would be amazed at the response of some of them when I point out some shit Apple does that make their products clearly lacking for the price, the cognitive dissonance is so strong they don't know how to react in any other way than lying or pretending it doesn't matter.
Your comment is literally more subjective, dismissive, and full of FUD than any other on on this thread. Check yourself.
Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
> complete independence of network connectivity and hence minimal latency.
Does it matter that each token takes additional milliseconds on the network if the local inference isn't fast? I don't think it does.
The privacy argument makes some sense, if there's no telemetry leaking data.
The heck do I do with an M4 in an iPad? Scroll hacker news really really fast? Apple needs to reinvest in software innovation on the iPad. I don't think my use case for it has evolved in 5 years.
I was hoping they would come out and say "and now developers can develop apps directly on their iPads with our new release of Xcode" but yeah, no. Don't know if the M4 with just 16GB of memory would be very comfortable for any pro workload.
There’s no way Apple would announce major new OS features outside of WWDC.
So, perhaps it’s no coincidence that a new iPadOS will be announced in exactly one month.
I’m far from an expert in Apple silicon, but this strikes me as having some conservative improvements. And in-depth info out there yet?
I'm guessing that the "ML accelerator" in the CPU cores means one of ARM's SME extensions for matrix multiplication. SME in ARM v8.4-A adds dot product instructions. v8.6-A adds more, including BF16 support. https://community.arm.com/arm-community-blogs/b/architecture...
Apple has the NPU (also called Apple Neural Engine), which is specific hardware for running inference. Can't be used for LLMs though at the moment, maybe the M4 will be different. They also have a vector processor attached to the performance cluster of the CPU, they call the instruction set for it AMX. I believe that that one can be leveraged for faster LLM inferencing.
Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
> In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending data up to the cloud for processing). Their primary business goal is to sell hardware. Yes, they’ve diversified into services and being a shopping mall for all, but it is about selling lu…
The MacBook Air is not a luxury device. That meme is out of date
Why are we running these high end CPUs on tablets without the ability to run pro apps like Xcode? Until I can run Xcode on an iPad (not Swift Playgrounds), it's a pass for me. Hear me out: I don't want to bring both an iPad and Macbook on trips, but I need Xcode. Because of this, I have to pick the Macbook every time. I want an iPad, but the iPad doesn't want me.
Just wait until you buy an Apple Vision Pro... [It's got the same restrictions as an iPad, but costs more than a MacBookPro.]
This is in fact the thing that stopped me from buying an Apple Vision Pro.
Seeing an M series chip launch first in an iPad must be result of some mad supply chain and manufacturing related hangovers from COVID. If the iPad had better software and could be considered a first class productivity machine then it would be less surprising but the one thing no one says about the iPads is “I wish this chip were faster”
To be honest, I wish my iPad's chip was slower! I can't do anything other than watch videos and use drawing programs on an iPad, why does it need a big expensive power hungry and environmentally impactful CPU when one 1/10 the speed would do? If I could actually do something with an iPad there would be a different discussion, but the operating system is so incredibly gimped that the most demanding task it's really su…
It has 6 efficiency cores. Every single of them is extremely power efficient, but still faster than an iPad 2-3 generations back. So unless you go full throttle, a M4 is going to be by far the most efficient CPU you can have.