NVIDIA launches open-source quantum AI models to advance computing
The company added that its models deliver up to 2.5 times faster performance and three times higher accuracy in decoding processes required for quantum error correction
15 April, 2026
TT
16
NVIDIA has unveiled what it describes as the world’s first open-source family of quantum artificial intelligence (AI) models, called NVIDIA Ising, aimed at accelerating the development of scalable and reliable quantum computing systems.
The new models are designed to help researchers and enterprises tackle two of the biggest challenges in quantum computing—processor calibration and quantum error correction—both critical to enabling real-world applications at scale.
NVIDIA said the Ising family provides high-performance, scalable AI tools that can improve the reliability of quantum processors, enabling hybrid quantum-classical systems to handle more complex workloads.
Jensen Huang, founder and chief executive officer of NVIDIA, said: “AI is essential to making quantum computing practical. With Ising, AI becomes the control plane — the operating system of quantum machines — transforming fragile qubits to scalable and reliable quantum-GPU systems.”
The company added that its models deliver up to 2.5 times faster performance and three times higher accuracy in decoding processes required for quantum error correction.
Addressing key engineering bottlenecks
The Ising platform includes specialised models for calibration and decoding:
Ising Calibration: A vision-language model that is significantly smaller than alternatives and can rapidly interpret quantum processor measurements to automate calibration
Ising Decoding: Two variants of a 3D convolutional neural network model optimised for either speed or accuracy, enabling real-time quantum error correction
These capabilities are intended to improve system stability and enable larger-scale quantum computations.
A range of global enterprises, academic institutions and research labs have already begun adopting the Ising models for quantum development. These include organisations such as Atom Computing, Harvard John A. Paulson School of Engineering and Applied Sciences, Fermi National Accelerator Laboratory, and Lawrence Berkeley National Laboratory, among others.
The models are also being deployed by universities including Cornell University, University of California San Diego and University of Chicago.
Supporting broader quantum ecosystem
NVIDIA is also offering supporting tools, including quantum computing workflows, training data and NVIDIA NIM microservices, enabling developers to fine-tune models for specific hardware architectures.
The Ising models integrate with NVIDIA’s broader quantum stack, including CUDA-Q software and NVQLink hardware interconnects, providing a full ecosystem for hybrid quantum-classical computing.
The global quantum computing market is expected to exceed $11bn by 2030, according to Resonance, with progress in error correction and scalability seen as key to unlocking commercial applications.
NVIDIA said the open-source nature of the Ising models will allow developers to retain full control over data and infrastructure, while accelerating innovation across the quantum computing landscape.





















