So, you could build Windows apps that run a GGUF model right on the PC without a separately running model server. Microsoft is adding experimental llama.cpp support to Windows ML, its toolkit for developers building local AI into Windows apps. So basically, bring your own model. Run inference locally. For example, connect speech recognition to text generation. More everyday apps using models on hardware you own. But this is an early implementation 🖥️ GGUF support validated on CPU and NVIDIA CUDA 🚫 No GGUF-to-NPU support ⚠️ The new text-generation API currently lacks temperature sampling, chat templates and speculative decoding llama.cpp does the inference underneath. Windows ML provides the application interfaces around it. Link in ALT.