I'm not the person you're replying to, but I wholeheartedly agree with them...

Quick background: doing AI inference requires three things. Lots of memory, lots of memory bandwidth, and of course plenty of compute that has access to that memory.

Quick reference: nVidia 5090 has 1,792 GB/sec bandwidth. 3090 gets about 1000 GB/sec. DGX Spark and AMD 395 whatever get about 275 GB/sec.

Apple M1 Max gets 400GB/sec, M5 Max gets 614GB/sec. Ultra variants get 2x that bandwidth, base variants get 1/2 that bandwidth. However... their compute is rather weak.

Right now, Apple's offerings are juuuuuust fast enough to run dense 27B models at usable speeds at like, 10% of the performance/watt of nVidia. They're world-leading general purpose CPUs but not killer GPUs.

By all accounts, these Windows PCs nVidia is touting seem to have DGX Spark like performance, which is less than impressive. Same with the upcoming AMD AI-oriented consumer stuff.

The other context here is that running your own AI at home is just starting to become feasible in terms of open model availability and the ability to run it at usable speeds. Many are interested in it for reasons of privacy, security, and cost certainty vs. buying tokens.

    Since Apple already sells unified memory systems, what 
    is the market opportunity you envision?

(And, let's face it. Even if nVidia did release a 6090 with 64-128GB of memory for an affordable price, consumers wouldn't get their hands on them anyway because people would just start filling data centers with them)

So.

Now you see Apple's opportunity, right? No data center sales to interfere with. No relationship with nVidia or AMD to worry about.

They could choose to make an absolute beast of a home AI machine. The M5 Ultra, if announced, might be that. It's admittedly a niche market, but people are already buying 64GB+ Macs faster than Apple can make them and they're fetching high prices on the used market as well.

The only real questions are if this market is even something Apple would find time to care about, and if they could secure enough DRAM to make a go at it. They are enormous obviously but they're feeling the RAM pinch just like everybody.

They use different technology for their VRAM though. Apple, AMD Strix and NVidia DGX/RTX Spark use LPDDR, whereas discrete cards will be either GDDR or HBM. That directly impacts the memory bandwidth figures. As for compute available, Apple and AMD still have very good figures there for what's essentially a general-purpose iGPU that ships as part of the stock system, rather than a special-purpose piece of dedicated hardware.

There’s something else. Memory size.

Even if a Mac isn’t the fastest in raw numbers it may be faster if it can load the whole model in its ram (went up to 512 GB before shortages) than a couple 32 GB cards could with the data having to be constantly loaded over PCI-E. Because unified memory means the Apple GPUs can access all 512 GB at full speed.

My understanding is this is the advantage that’s pushing huge Mac Studio demand. Because it was the only way to give GPUs so much memory at price points anywhere near.

Yeah you can do way better once you’re in the 5 digits. But below that Apple had a specific advantage for some.