Local models, developer control, and the future of AI runtimes | BRK235
Local AI models Hybrid AI execution Microsoft Build 2026 AI runtimes OpenClaw MLX Quantization AI privacy Model deployment Developer tools NVFP4 Local inference
This Microsoft Build 2026 session explores how local and hybrid AI model execution is transforming developer workflows. It covers OpenClaw for easy local deployment, MLX for Apple devices, quantization techniques including NVFP4, and real-world use cases in media, manufacturing, and automotive industries. Ideal for developers seeking to build privacy-focused AI applications with full control over model execution.