logoalt Hacker News

yw3410yesterday at 7:04 PM1 replyview on HN

How small a model are we talking? Don't even the smallest models which would work need gigabytes of memory?


Replies

lelanthranyesterday at 9:27 PM

> How small a model are we talking? Don't even the smallest models which would work need gigabytes of memory?

I dunno, for game prose I expect that a tiny highly quantized model would be sufficient (generating no more than a paragraph), so 300MB - 500MB maybe? Running on CPU not GPU is feasible too, I think.