Commonwealth Fusion Systems (CFS) announced on Tuesday at CES 2026 that it has installed the first of 18 magnets in its Sparc fusion reactor, a key milestone in its effort to achieve net energy gain from fusion power. The magnet, weighing 24 tons, is designed to generate a 20-tesla magnetic field—about 13 times stronger than a typical MRI machine—essential for confining and compressing superheated plasma inside the reactor’s doughnut-shaped chamber. The Sparc reactor, which CFS aims to activate next year, represents a major step toward realizing practical fusion energy. If successful, the plasma inside will burn at over 100 million degrees Celsius while producing more energy than required to initiate and sustain the reaction—a breakthrough known as net energy gain. The magnets will be cooled to -253°C (-423°F) to enable superconductivity, allowing them to carry over 30,000 amps of current safely. Once fully assembled by summer, the magnets will sit atop a 75-ton stainless steel cryostat, which was installed last March. To refine the reactor’s design and anticipate operational challenges, CFS has partnered with Nvidia and Siemens to develop a digital twin of Sparc. Siemens is providing design and manufacturing software, while Nvidia’s Omniverse platform will integrate real-time data from the physical reactor into the simulation. This digital twin will allow engineers to run experiments and adjust parameters virtually before applying changes to the actual machine, enabling faster learning and safer testing. Bob Mumgaard, CFS co-founder and CEO, emphasized that this integration marks a shift from isolated simulations to continuous, real-time comparison between digital and physical systems. “It’ll run alongside so we can learn from the machine even faster,” he said. Building Sparc has been expensive. The company has raised nearly $3 billion to date, including an $863 million Series B2 round in August backed by Nvidia, Google, and more than three dozen other investors. Its next phase, the commercial-scale Arc plant, is expected to cost several billion dollars more. Mumgaard stressed that advancements in AI and digital twin technology could accelerate fusion development. “As machine learning tools get better and representations become more precise, we can see it go even faster,” he said. “We have an urgency for fusion to get to the grid.” If successful, Sparc could pave the way for clean, abundant energy from fusion, offering a sustainable alternative to fossil fuels and traditional nuclear fission.