Comment

Comment by zozbot234

32B active is nothing special, there's local setups that will easily support that. 1T total parameters ultimately requires keeping the bulk of them on SSD. This need not be an issue if there's enough locality in expert choice for any given workload; the "hot" experts will simply be cached in available spare RAM.
parent zozbot234 9 months ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton