Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs
Trending on Hacker News: Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs (147 points / 60 comments, via github.com)
In one line
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
Opening excerpt
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Uh oh! There was an error while loading. Please reload this page .
argonautlabsai / deltafin Public forked from gavamedia/deltafin Notifications You must be signed in to change notification settings Fork 0 Star 23 main Branches Tags Go to file Code Open more actions menu Latest commit History 42 Commits 42 Commits Folders and files Name Name Last commit message Last commit date .github/ workflows .github/ workflows docs docs k3-public-bench k3-public-bench native native research/ study research/ study tools tools .gitignore .gitignore CREDITS.md CREDITS.md Cargo.lock Cargo.lock Cargo.toml Cargo.toml LICENSE LICENSE README.md README.md View all files Repository files navigation ARGODRIVE Deltafin A fork of gavamedia/deltafin (MIT) running Kimi K3 from SSDs on Apple Silicon, with the ARGODRIVE storage work.
(Excerpted from the original; full article via the source link below.)
This story hit the Hacker News front page today (147 points / 60 comments, via github.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.
Source: Hacker News