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
NewsSiMa.ai details Palette 3.0 for concurrent edge AI workloads
Newsllama.cpp and ggml reach v1.0.0, set rules for breaking changes
NewsLiquid AI releases LFM3 family for on-device multimodal AI
NewsRecursive releases Flint open-weight coding model for local hardware
NewsHugging Face releases AnyLanguageModel 1.0 for Apple platforms
NewsGoogle DeepMind and Singapore build on-device AI scam detector
NewsLiquid AI releases 24B mixture-of-experts model for on-device agents
NewsGoogle launches offline AI Edge Foresight note-taking app for Mac
NewsLiquid AI releases d1 models for single-pass edge decisions
NewsGoogle releases EmbeddingGemma 2 for on-device multimodal search
NewsRemoveMacAI uses a reversible profile to disable Apple Intelligence on macOS 27
NewsNVIDIA sets October 23 launch for 64GB DGX Spark at $4,999
