Nvidia has announced its new Rubin CPX chip system, designed to accelerate demanding artificial intelligence tasks such as video generation and software creation. The new GPU is expected to launch at the end of 2026. The company's chips and systems are at the core of the artificial intelligence computing boom. The system is designed to handle demanding tasks such as video generation and software creation.
The DGX Spark, powered by the NVIDIA GB10 Grace Blackwell Superchip, delivers 1 petaFLOP of AI performance. It comes preinstalled with the NVIDIA AI software stack and 128GB of memory, allowing developers to prototype, fine-tune, and perform inference on AI models with up to 200 billion parameters locally. Workloads can be migrated to NVIDIA DGX cloud or other NVIDIA accelerated data centres or cloud infrastructures. High-performance NVIDIA ConnectX networking enables connecting two NVIDIA DGX Spark systems together to work with AI models up to 405 billion parameters.
Nvidia DGX Spark is also suited for developing edge applications with NVIDIA AI frameworks like Isaac and Metropolis, making it an excellent platform for robotics, smart cities, and computer vision solutions. The company says leading system manufacturers are set to build NVIDIA DGX Spark and DGX Station systems.
