[dontwearitout]

It's great for AI. Today's large language models are very hungry for RAM. Consumer electronics have been rocking just a few GB of RAM for the last decade because there was no real usecase for 100+GB, but that has changed since GPT3 came along. We'll likely see large language and image models integrated into all sorts of software stacks.

[petra]

Doesn't it need to be complemented by enough bandwidth to be useful ?

[rbanffy]

Good point. With a 1TB module it's foolish to have a 1TB server. It's wiser to fill all memory slots than having one very large module.

OTOH, a 16TB per socket server would be quite a beast.