#on-device-ai
Every summary, chronological. Filter by category, tag, or source from the rail.
Building AI-Powered Android Apps with Gemini Nano
Android developers can leverage Gemini Nano via the AI Core system service for on-device inference, or use hybrid inference to fall back to cloud models, ensuring privacy and efficient resource management without managing model deployment.
AI EngineerFine-Tuning Tiny LLMs for On-Device AI Agents
Developers can achieve production-grade performance on-device by choosing between system-level models (Gemini Nano) for general tasks or fine-tuning tiny LLMs (<1B parameters) via LiteRT-LM for specialized, high-accuracy agentic workflows.
AI EngineerMLX: Frontier AI Fully On-Device on Apple Silicon
MLX runs real-time vision, <100ms TTS, omni models, 426B LLMs, and text-to-video on 16GB Mac VRAM—no cloud. Turbo Quant cuts KV cache 4x for 1M contexts, enabling accessibility and robots in low-connectivity areas.
AI EngineerShowing 3 of 3