PinnedInGoogle Developer ExpertsbySasha Denisov·Oct 5Fine-Tuning Small Models for On-Device Agents: Train, Convert, and Measure What ChangedHow litetune rebuilds the LoRA-to-device workflow and measures the model that actually ships.A response icon1A response icon1
Sasha Denisov·Oct 9Robotic Memory and Qdrant EdgeVector search inside a Reachy: what the robot remembers, what it costs on four cores, and where memory stops being a database pulls several…
Sasha Denisov·May 31Hybrid AI in Flutter: Routing Between On-Device and Cloud ModelsA tour of the options — and how I do it with Genkit DartA response icon2A response icon2
InGoogle Developer ExpertsbySasha Denisov·Feb 21On-Device RAG for App Developers: Embeddings, Vector Search, and BeyondGiving your Offline AI agent memory — the ability to search and retrieve your private dataA response icon6A response icon6
InGoogle Developer ExpertsbySasha Denisov·Dec 29, 2025On-Device Function Calling with FunctionGemmaA Practical Guide to preparing and using Google’s smallest function calling model for Mobile and Web DevelopersA response icon1A response icon1
Sasha Denisov·Aug 21, 2025The Dawn of Offline AI Agents in Your PocketComplete Guide to flutter_gemma PluginA response icon2A response icon2
InGoogle Developer ExpertsbySasha Denisov·Feb 3, 2025Fine-Tuning Gemma with LoRA for On-Device Inference (Android, iOS, Web) with Separate LoRA WeightsPrologueA response icon5A response icon5
InFlutter CommunitybySasha Denisov·May 6, 2022Flutter for Apple TVNOTE: Maintaining support for upcoming Flutter versions like 3.27 and 3.29, stable build pipeline, and Firebase support takes time and…A response icon4A response icon4
InFlutter CommunitybySasha Denisov·Jul 3, 2019Deep Links and Flutter applications. How to handle them properly.Some time ago I faced the task of launching a Flutter application using Deep links and I worked with the documentation and experimented to…A response icon28A response icon28