It's not even just that. If you just built the rom chips separately and swapped them for the RAM of a normal accelerator, it would not help at all.

The trick is that every compute element in their system has it's own small pool of ROM, instead of putting all the ram behind a common pipe. ROM is just used because it's the densest kind of memory that can be fabricated on the same process as their logic.

I thought DRAM was pretty dense already. Is mask ROM that much denser?

Yes, each rom bit can be a transistor or even a diode with a decoder circuit. Simplest Dram cell is capacitor+transistor - and you need a clock, refresh circuit etc.

Someday, I imagine model weights could even be encoded as analog resistors (memristors or similar) for even greater density

Hm. I wonder how many relays I'd need to make a physical MNIST classifier. That'd be dope