Real-time, local conversational AI is how we will democratize intelligence.
This is a dev post classified by AGK Intelligence as Mobile & desktop (a launch), kept by the Dev Radar because it carries real work, not commentary.
Real-time, local conversational AI is how we will democratize intelligence. We just ported LFM3-Omni-2B by @LiquidAI to run fully offline on my iPhone 18 Pro Max at ~80 tok/s, powered by custom WebGPU kernels in a React Native app. Should we release this on the App Store? 👀
Posted by Xenova (21.1k followers) 3 h ago · 112 likes · 8.4k views · view the original post on X. Kept by the Dev Radar as Mobile & desktop.
More dev work like this
- SSHPeaches is back in beta after I fixed the policy issues. — @Zenul_Abidin
- First SwiftUsage PR - merged! — @blueemi99
- grok bot can now live on your mac — @everestchris6
- 论文里的公式看着不复杂，真要敲进 LaTeX，分式、上下标、矩阵一个个写，没多久就被括号绕晕。 — @GitHub_Daily
- ¡Juega con tu biblioteca de Steam en macOS! — @midudev
- tinkering with an @omarchy menubar plugin for omafeed: — @p_ch
- 😱惊了！以后别再找各种下载器了！这个开源神器直接把“下载任何东西”变成粘贴即得！所有付费课程都可免费白嫖！ — @NFT_Chen
- I updated SSHPeaches to resolve the foreground permission issues. — @Zenul_Abidin
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 19:29 UTC. Full method.