Nvidia, Microsoft Expand Local AI Support with New RTX Spark Line
Nvidia and Microsoft have expanded support for running AI agents locally on NVIDIA hardware, alongside new Windows PCs in the RTX Spark line. This move aims to reduce barriers for users installing local models and make AI processing more accessible.
The companies have partnered with software partners to simplify installation for local agent software, such as Hermes Agent, OpenClaw, and Perplexity Portable Computer. These agents will offer one-click local setup across RTX and DGX systems on Windows, reducing manual configuration and making it easier for users to run AI models locally.
Nvidia has also targeted performance in the open-source inference stack with new work on llama.cpp and vLLM communities. The updates deliver up to 1.9 times higher throughput on GeForce RTX 5090 GPUs, improving local agent workloads across various systems.