Comment

Comment by girvo

Not quite: not all of this needs to be in VRAM

It has a set of n-gram tables which you can stream from system RAM or even NVMe

That said it’s still quite big! I can’t fit it on my DGX Spark, though I believe you can if you have two?

parent girvo 23 days ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton