They have, because until now Apple Silicon was the only practical way for many to work with larger models at home because they can be configured with 64-192GB of unified memory. Even the laptops can be configured with up to 128GB of unified memory.

Performance is not amazing (roughly 4060 level, I think?) but in many ways it was the only game in town unless you were willing and able to build a multi-3090/4090 rig.

I would bet that people running LLMs on their Macs, today, is <0.1% of their user base.

People buying Macs for LLMs—sure I agree.

Since the current MacOS comes built in with small LLMs, that number might be closer to 50% not 0.1%.

I'm not arguing whether or not Macs are capable of doing it, but whether is a material force that drives people to buy Macs because of it; it's not.

Higher than that buying the top end machines though, which are very high margin

All macs? Yes. But of 192GB mac configs? Probably >50%

I'm currently wondering how likely it is I'll get into deeper LLM usage, and therefore how much Apple Silicon I need (because I'm addicted to macOS). So I'm some way closer to your steel man than you'd expect. But I'm probably a niche within a niche.

Tons of people do, my next machine will likely be a Mac for 60% this reason and 40% Windows being so user hostile now.

my $5k m3 max 128gb disagrees

Doubt it, a year ago useful local LLMs on a Mac (via something like ollama) was barely taking off.

If what you say it's true you were among the first 100 people on the planet who were doing this; which btw, further supports my argument on how extremely rare is that use case for Mac users.

No, I got a MacBook Pro 14”with M2 Max and 64GB for LLMs, and that was two generations back.

People were running llama.cpp on Mac laptops in March 2023 and Llama2 was released in July 2023. People were buying Macs to run LLMs months before M3 machines became available in November 2023.