Edge
Research papers, repositories, and articles about edge
Showing 6 of 6 items
Gemma 4 on Edge: Running Multimodal AI on Mobile, Raspberry Pi & IoT Devices
Walks through running Gemma 4’s edge models on phones, Pis, and Jetson boards. Covers quantization, latency numbers, and when to stay off the cloud.
Crosstalk-Solutions/project-nomad
Project N.O.M.A.D is an offline "survival computer" stuffed with tools, knowledge, and AI models. It targets low-connectivity or crisis settings. This is a concrete template if you’re thinking about AI systems that must work without the cloud.
google-ai-edge/LiteRT-LM
Runtime for running language models efficiently on edge hardware. Targets phones, Jetson-class boards, and other low-power devices.
google-ai-edge/gallery
Showcases on-device ML and generative AI demos that run locally. Good starting point if you want examples of production-ready edge AI apps.
STResNet & STYOLO: A New Family of Compact Classification and Object Detection Models for MCUs
STResNet and STYOLO target microcontrollers, hitting competitive ImageNet and COCO scores with just a few million parameters. If you care about on-device vision, these architectures offer stronger accuracy–latency tradeoffs than classic MobileNet-style baselines.
jomjol/AI-on-the-edge-device
Firmware that reads analog meters and similar devices with a tiny on-device vision model. It’s a practical template for bringing AI to legacy hardware.