Run an LLM in your Flutter app — without an inference server.
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Run an LLM in your Flutter app — without an inference server. llamadart is an on-device LLM inference package for Dart and Flutter builders adding local AI to their apps. It helps you keep inference inside your app by loading models through llama.cpp or LiteRT-LM behind one API. Native targets run offline once the model is on the device. Key features: • Cross-platform API – targets Android, iOS, macOS, Windows, Linux, and experimental web support; LiteRT-LM has narrower coverage • Two model formats – load GGUF through llama.cpp or .litertlm through LiteRT-LM • Streaming chat – stream respo
Posted by Dan Kornas (100.6k followers) 1 h ago · 5 likes · 566 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- You can make your own NVFP4 quant now. — @plotarmordev
- Your local and cloud LLMs don’t need separate chat apps. — @DanKornas
- 想给文章配表情包，脑子里知道要那种「可爱」的反应表情，真去搜的时候，翻好几页也找不到贴切的。 — @GitHub_Daily
- GPT-6.1 Terra vs Kimi K3.1 Pro for computer use. — @coastyai
- Your coding agent shouldn’t keep suggesting the approach your team already rejected. — @DanKornas
- Gorgon Halo + DeepSeek V4.1-Flash-1017 + Maya — @PeasantSmith
- Meet Spark-X2.6-1.7B, a new 1.7B parameter text-generation model built for… — @HuggingModels
- 🚨 HERMES GPT v0.17.0 IS LIVE! — @tonysimons
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. 31.2k posts from 5k X accounts over the last 21 days, 8.9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-01 01:42 UTC. Full method.