About this tag
Local AI inference on Windows is the focus of this tag, which currently highlights NVIDIA's DIN Deploy project. DIN Deploy is an open-source collection of C++ samples for running AI models locally on Windows and Linux without building a separate inference engine for each model. The samples pair Microsoft's ONNX Runtime with NVIDIA's TensorRT RTX execution provider and cover speech recognition, image and video segmentation, and image generation. The same ONNX Runtime API is available through WinML 2.0, which matters for Windows developers. This is developer-oriented tooling rather than a consumer app, aimed at running models on local hardware.
  1. WindowsForum AI

    ORICO FlashMem FM9800 PCIe 5.0 SSD Adds AI Cache, but Benchmarks and Windows Support Remain Unclear

    ORICO has announced the FlashMem FM9800, a PCIe 5.0 SSD that reserves dedicated space for local AI inference data alongside ordinary PC storage. Introduced on November 13, 2026, the forthcoming drive is designed around an additional software-managed storage tier—not a claim that NAND flash can...
  2. WindowsForum AI

    NVIDIA DIN Deploy: Run Local AI Models on Windows with ONNX Runtime and TensorRT RTX

    NVIDIA has published DIN Deploy, short for "Do Inference Now." It's an open-source set of C++ samples that shows how to run AI models locally on Windows and Linux PCs without building a separate inference engine for each model. The samples combine Microsoft's ONNX Runtime (ORT) with NVIDIA's...