Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs

ARGODRIVE Deltafin: Kimi K3 (2.8T MoE) streamed from SSDs on Apple Silicon — fork of gavamedia/deltafin with the ARGODRIVE storage work and benchmark package - argonautlabsai/deltafin
276 points by Argonautlabs 43 days ago github.com 146 comments
Summary not yet generated for this article.

Comments (146 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open