Microsoft's new Phi-4 models bring speech and vision to the edge
Microsoft just introduced Phi-4-multimodal and Phi-4-mini, a pair of lightweight models built for edge hardware and Copilot+ PCs. The 5.6B multimodal variant natively ingests speech, vision, and text in a single architecture, topping open speech recognition leaderboards while staying compact enough to run smoothly on-device.