Build, Optimize, Run: The Developer's Guide to Local Gen AI on NVIDIA RTX AI PCs

The AI PC ecosystem is exploding. Developers are now running local, high-performance AI workloads. This technical session dives into how NVIDIA accelerates the top open-source software stack—from the different quantization techniques, training recipes, as well as inference frameworks and tools like Ollama, ComfyUI and custom pipelines. Crucially, we will move beyond simple inference to address the architecture of reliable, local agentic workflows. Join us to learn about the technical intricacies and considerations to develop robust, local AI workflows on NVIDIA RTX. Access resources for AI on NVIDIA RTX PCs: https://developer.nvidia.com/ai-apps-for-rtx-pcs