Running a 180B parameter LLM on a single Apple M2 Ultra

Even a linear growth rate of average RAM capacity would obviate the need to run current SOTA LLMs remotely in short order.

Historically average RAM has grown far faster than linear, and there really hasn't been anything pressing manufacturers to push the envelope here in the past few years... until now.

It could be that LLM model sizes keep increasing such that we continue to require cloud consumption, but I suspect the sizes will not increase as quickly as hardware for inference.

Given how useful GPT-4 is already. Maybe one more iteration would unlock the vast majority of practical use cases.

I think people will be surprised that consumers ultimately end up benefitting far more from LLMs than the providers. There's not going to be much moat or differentiation to defend margins... more of a race to the bottom on pricing

RAM is easy. The hard part is making the unified memory SOC like Apple's. From what I know, Apple performance is almost magic. And whatever Apple is making, they are at peak capacity already and they can't make more even if they want to. Nobody else has a comparable technology. Apple is in its own league.