Yeah, I'm optimistic we're getting really close to "forever laptops" once competing hardware catches up on efficiency.

What do I need any higher specs for, other than battery life?

As someone who does a lot of work with local LLM's, today's systems feel woefully under-powered. I'm looking forward to a future where my laptop has 10x the memory, 100x the memory bandwidth, and optimized cores to make inference workflows that currently take minutes or hours go down to seconds or milliseconds.

While we're at the point where traditional software is pretty much fast enough for all but extreme use-cases, with LLM's it feels like we're back to the days where you press compile and go have a coffee or chat to your colleague.

	▲	simonask 37 minutes ago \| parent [-]
		Right now there isn’t really a convincing use case for local LLMs outside of enthusiast or specific niches. It takes a lot of expensive hardware, and most people don’t have extreme enough requirements to recoup that investment. That might change, but it would require either that hardware gets much cheaper or everyone’s demands for LLMs increase significantly.