Nexa SDK #
Run, build & ship local AI in minutes
84 комментариев7:01 AM
Nexa SDK runs any model on any device, across any backend locally—text, vision, audio, speech, or image generation—on NPU, GPU, or CPU. It supports Qualcomm and Apple NPUs, GGUF, Apple MLX, and the latest SOTA models (Gemma3n, PaddleOCR).