Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by jnovek

1 day ago

I think that’s only true for MoE models. A dense model like 3.6 27b will require more (plus a KV store).

1 comment

jnovek

Reply

bityard  1 day ago

No, even MoE models need to fit into (V)RAM. MoE has faster inference because only a subset of layers are used to predict the next token, but the set of layers used changes with every token.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities