NVIDIA Ising: World’s first open AI models aimed at quantum computing

- The NVIDIA Ising open model family delivers AI-based quantum processor calibration capabilities, as well as fast quantum error-correction decoding

- Leading quantum enterprises, academic institutions and research labs are adopting Ising, including Academia Sinica and Yonsei University

Source: NVIDIA. Image representing the NVIDIA Ising quantum AI model family.

NVIDIA has announced the world’s first family of open source quantum AI models, NVIDIA Ising, designed to help researchers and enterprises build quantum processors capable of running real-world applications.

To achieve useful quantum applications at scale, significant breakthroughs are still needed in quantum processor calibration and quantum error correction, NVIDIA said. AI will be key for turning today’s quantum processors into large-scale, reliable computers, while open models empower developers to build high-performance AI while maintaining total control over their data and infrastructure.

Named after a landmark mathematical model that dramatically simplified the understanding of complex physical systems, the NVIDIA Ising family provides high-performance, scalable AI tools for quantum error correction and calibration. Ising models deliver up to 2.5x faster performance and 3x higher accuracy for the decoding process needed for quantum error correction.

“AI is essential to making quantum computing practical,” said Jensen Huang, founder and CEO of NVIDIA.

“With Ising, AI becomes the control plane — the operating system of quantum machines — transforming fragile qubits to scalable and reliable quantum-GPU systems.”

NVIDIA Ising includes state-of-the-art customisable models, tools and data that accelerate quantum processors:

- Ising Calibration: A vision language model that can rapidly interpret and react to measurements from quantum processors. This enables AI agents to automate continuous calibration, reducing the time needed from days to hours. 

Ising Decoding: Two variants of a 3D convolutional neural network model — optimised for either speed or accuracy — to perform real-time decoding for quantum error correction. Ising Decoding models are up to 2.5x faster and 3x more accurate than pyMatching, the current open source industry standard.

Leading enterprises, academic institutions and research labs are adopting Ising for quantum computing development. Ising Calibration is already in use by Atom Computing, Academia Sinica, EeroQ, Conductor Quantum, Infleqtion, IonQ, IQM Quantum Computers, and Q-CTRL.

Ising Decoding is being deployed by EdenCode, Infleqtion, IQM Quantum Computers, Quantum Elements, SEEQC, and Yonsei University.

In addition, NVIDIA is providing a cookbook of quantum computing workflows and training data along with NVIDIA NIM microservices, equipping developers to finetune models for specific hardware architectures and use cases with minimal setup. The models can also run locally on researchers’ systems, protecting proprietary data.

NVIDIA Ising complements the NVIDIA CUDA-Q software platform for hybrid quantum-classical computing and integrates with the NVIDIA NVQLink QPU-GPU hardware interconnect for real-time control and quantum error correction, providing researchers and developers with a full suite of tools to turn today’s qubits into tomorrow’s accelerated quantum supercomputers.

The quantum computing market is expected to surpass US$11 B in 2030, according to analyst firm Resonance. This growth trajectory is highly dependent on continued progress in addressing critical engineering challenges like quantum error correction and scalability.

Explore

NVIDIA Ising joins NVIDIA’s open model portfolio, which includes NVIDIA Nemotron for agentic systems, NVIDIA Cosmos for physical AI, NVIDIA Alpamayo for autonomous vehicles, NVIDIA Isaac GR00T for robotics and NVIDIA BioNeMo for biomedical research.

These open models, data and frameworks are available on GitHub, Hugging Face and build.nvidia.com