Flutter Nantes Meetup #23 : Edge AI in Flutter: How Far Have We Come?
📅 September 24, 2026 / 19h-22h
📍 Nantes, hosted by SNCF Connect
We're thrilled to welcome Sasha Denisov for our 23rd meetup, with a talk that traces the entire evolution of on-device AI in Flutter: "Edge AI in Flutter: How Far Have We Come?"
Two years ago, when flutter_gemma first shipped, on-device AI in Flutter meant a MobileNet-style vision classifier and a small text-only LLM answering one prompt at a time, with no images, no tools, and no memory.
Fast forward to 2026, and the landscape is almost unrecognizable: phones now run multimodal open models, like Gemma, Qwen, Llama and more, that see images, call tools, retain context, and retrieve from a local knowledge base, fully offline, with nothing leaving the device.
In this talk, Sasha takes us on a retrospective across the models, the runtimes powering them (LiteRT-LM, MediaPipe, llama.cpp, ONNX Runtime, and even OS-native models), and the Dart packages that brought it all natively into Flutter.
Using flutter_gemma as a throughline, we'll see how it grew from a thin MediaPipe wrapper around a 2B model into a full modular ecosystem, complete with pluggable engines, embeddings, on-device RAG, and agents capable of calling tools, running skills, and speaking MCP.
What you'll walk away with:
- How the model landscape shifted from single-purpose, text-only tools to multimodal, tool-using models running fully offline
- A complete map of the Flutter edge-AI ecosystem: runtimes, flagship packages (flutter_litert, flutter_gemma), and the surrounding plugins for RAG, agents, embeddings, and ML Kit
- What's only become possible recently: on-device RAG, multimodal input, and real agent loops calling MCP tools locally
- Where it's all heading, and what's genuinely production-ready today
***
A huge thank you to Zenika for the video recording equipment, and to SNCF Connect for hosting us and providing catering and drinks for the evening.
See you all on September 24 in Nantes! 🚀
