Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
Unofficial Hacker News client; not affiliated with Y Combinator.
dghlsakjg · · focus · HN ↗
People will keep plugging away at this and figure out how to avoid wearing the hard drive, how to make it run faster, custom hardware buses etc.
Keep going! I personally can't wait for the day when a 1t param model runs off a $200 SSD instead of a $50k rack of Nvidia chips.
myrmidon · · focus · HN ↗
Has also been the case for things like chess computing; a lot of the progress we made over the last decades there (even before involving neural networks!) happened thanks to software improvements because the problem got so accessible, not just faster hardware.
I expect similar trends with AI; I'd expect to get decent, human comparable capability with <200GB/s of memory bandwidth and under 60GB of RAM long term (SSDs with very high read bandwidth looks also promising, but we'll see).
I hope that in a decade or two, training will also be somewhat feasible for "pro-sumers".
Bayart · · focus · HN ↗
That's how the AI boom came around to start with, before CUDA it was an academic topic.
mannanj · · focus · HN ↗
RachelF · · focus · HN ↗
So true. The reverse is also true - when greedy companies overprice their initial release so that it is out of range of the enthusiastic hobbyist they stall progress and adoption.
This is true for hardware (eg failed Intel Optane, Knights Bridge) and software that does not have a cheap or free basic plan.