NVIDIA Launches Ising: First Open Quantum AI Model Family

NVIDIA has officially launched NVIDIA Ising, the world’s first family of open quantum AI models designed to bridge the gap between experimental quantum hardware and practical, real-world applications. By leveraging artificial intelligence to address the critical engineering bottlenecks of quantum calibration and error correction, the Ising model family aims to transform how researchers and enterprises manage the sensitivity of quantum processors.

Automating Quantum Calibration

The Ising Calibration component functions as a vision language model, a multimodal architecture designed to interpret and react to diagnostic measurements from quantum hardware. By acting as an autonomous AI agent, it continuously monitors system readouts and makes real-time adjustments to ensure optimal performance. This automation is a significant advancement for the field, as it reduces the time required for continuous calibration from days to hours, effectively removing a major bottleneck in quantum hardware development.

Advancing Error Correction

To address the challenge of environmental noise and rapid error accumulation in qubits, NVIDIA has introduced Ising Decoding. This component utilizes 3D convolutional neural networks (3D CNNs) to perform real-time quantum error correction. Available in two variants—one optimized for speed and the other for accuracy—these models allow researchers to infer the correct state of a quantum system despite noisy observations. Compared to the current industry standard, pyMatching, Ising Decoding models have demonstrated up to 2.5x faster performance and 3x higher accuracy.

Ecosystem Integration and Adoption

The Ising model family is designed to integrate directly into NVIDIA’s existing quantum-classical ecosystem. It complements the CUDA-Q software platform, which provides a programming model for hybrid workflows, and utilizes the NVQLink QPU-GPU hardware interconnect to facilitate the low-latency communication required for real-time error correction. These models are available on GitHub, Hugging Face, and build.nvidia.com, with support for fine-tuning via NVIDIA NIM microservices.
Day-one adoption of the technology is already widespread across the quantum research and commercial sectors. Ising Calibration is currently being utilized by organizations including Atom Computing, Academia Sinica, EeroQ, Conductor Quantum, Fermi National Accelerator Laboratory, Harvard John A. Paulson School of Engineering and Applied Sciences, Infleqtion, IonQ, IQM Quantum Computers, Lawrence Berkeley National Laboratory’s Advanced Quantum Testbed, Q-CTRL, and the U.K. National Physical Laboratory. Meanwhile, Ising Decoding is being deployed by institutions such as Cornell University, EdenCode, Sandia National Laboratories, SEEQC, the University of California San Diego, UC Santa Barbara, the University of Chicago, the University of Southern California, and Yonsei University, among others.