On-Device AI
On-device AI runs model inference on the hardware where a person or application uses it.
Follow local inference on laptops, phones, and edge devices. Coverage explains the trade-offs among latency, privacy, model size, power, and hardware support.
Latest coverage
Articles
NewsPrismML's 1-bit Bonsai 27B, a 27B-class model that runs on an iPhone, draws developer attention
NewsMultiverse debuts tiny AI models that run offline without compromising performance
NewsSalva Health's screening device has the potential to bridge the breast cancer mortality gap
NewsMistral AI launched the compact 'les Ministraux' models for edge use cases
NewsHugging Face's SmolLM is a family of powerful models small enough to run on your device
NewsGoogle's June Feature Drop brings Gemini Nano to Pixel 8 and 8a devices
NewsApple Intelligence integrates context-aware AI across iOS 18, iPadOS 18, and macOS Sequoia
NewsNVIDIA at Computex 2024: RTX AI Toolkit developer preview
NewsNVIDIA at Computex 2024: Project G-Assist launch
NewsMicrosoft unveiled a new category of AI-optimized Windows PCs
NewsNVIDIA ChatRTX's latest update brings support for additional features and models