Tag
8 articles
This article explains FreeToken, an edge-native serving engine that enables large MoE models to run on a single workstation GPU by intelligently managing cache misses through PCIe bandwidth and CPU execution.
Explore the advanced AI concepts behind Needle 2, a 45-million-parameter model that runs efficiently on minimal hardware. Learn how tool calling, quantization, and edge deployment are revolutionizing AI accessibility.
This explainer examines how Apple's disruption of the mid-tier watch market serves as a precedent for its potential impact on the $200 billion eyewear industry, focusing on AI integration in smart eyewear.
Google introduces the Coral Board, a compact single-board computer that runs Gemma 3 locally, enabling on-device AI inference for edge computing applications.
This article explains vision-language models and how Liquid AI's new LFM2.5-VL-450M model brings powerful AI capabilities to edge devices.
This explainer explores how AI-powered sensor systems automatically determine when and how to clean earbuds, demonstrating advanced concepts in machine learning, sensor fusion, and embedded artificial intelligence.
NullClaw is a 678 KB AI agent framework built in Zig, running on just 1 MB RAM and booting in two milliseconds, showcasing extreme efficiency in edge AI development.
Google introduces Nano Banana 2, a more efficient image generation and editing model that reduces computational requirements while maintaining high quality.
