Running Kimi K3 on a M1 Mac
Hacker News 热议:Running Kimi K3 on a M1 Mac(10 赞 / 0 评论,来源 github.com)
一句话概要
Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents. - gavamedia/deltafin
原文开头节选
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 .
gavamedia / deltafin Public Notifications You must be signed in to change notification settings Fork 4 Star 36 main Branches Tags Go to file Code Open more actions menu Folders and files Name Name Last commit message Last commit date Latest commit History 9 Commits 9 Commits research/ study research/ study tools tools .gitignore .gitignore BRAINSTORM-SPEED.md BRAINSTORM-SPEED.md LICENSE LICENSE PLAN.md PLAN.md README.md README.md View all files Repository files navigation ____ _ _ __ _ | _ \ | | | __ _ / () __ | | | |/ _ \ | / ` | || | ’ \ | || | __/ | || (| | | | | | | |/ _||__,|| ||| |_| An experiment in running Kimi K3 (2.8T parameters) on one Apple Silicon Mac Deltafin is a small research project that runs a Mixture-of-Experts model …
(以上为原文节选,完整内容见下方”原文来源”)
这条动态今日登上 Hacker News 首页(10 赞 / 0 评论,来源 github.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。
原文来源: Hacker News