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
NewsLiquid AI brings DSpark speculative decoding to LFM2.5-VL-3B
NewsHugging Face adds llama.cpp GGUF support to Transformers
NewsPrismML releases Bonsai 2 27B under Apache 2.0 for local AI
NewsPerplexity brings Portable Computer to Windows RTX PCs
NewsPerplexity adds hybrid cloud-and-local AI processing to its Mac app
NewsApple extends Apple Intelligence into redesigned Health app
NewsNVIDIA launches PAIR beta to distribute local AI inference across home PCs
NewsHugging Face releases 207 WebGPU kernels for local AI
NewsApple launches M6 and M5 Pro Mac mini for local AI workloads
NewsGoogle DeepMind brings on-device sign-language translation to the Pixel 11
NewsLiquid AI ships LFM2.5-2.6B, a 2.6B on-device model it says rivals ones nearly four times bigger
NewsNativ, an open-source macOS app, runs frontier open AI models locally on Apple Silicon