NVIDIA has unveiled Ising, described as the world’s first family of open-source quantum AI models designed to help researchers and enterprises build practical, scalable quantum processors.
Announced on April 14, 2026, the Ising model family includes two key components:
– Ising Calibration — a vision-language model that automates quantum processor calibration.
– Ising Decoding— which uses 3D convolutional neural networks for quantum error correction.
According to NVIDIA, Ising Decoding delivers up to 2.5 times faster performance and 3 times higher accuracy compared to pyMatching, the current open-source industry standard for error correction.
AI as the Control Plane for Quantum Systems
NVIDIA founder and CEO Jensen Huang 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 into scalable and reliable quantum-GPU systems.”
The models integrate seamlessly with NVIDIA’s CUDA-Q platform for hybrid quantum-classical computing and the NVQLink hardware interconnect for QPU-GPU systems.
Adoption and Availability
Several leading institutions and companies have already begun adopting Ising, including Academia Sinica, Fermi National Accelerator Laboratory, Harvard John A. Paulson School of Engineering and Applied Sciences, Infleqtion, IQM Quantum Computers, Lawrence Berkeley National Laboratory’s Advanced Quantum Testbed, and the UK National Physical Laboratory.
The models are now openly available on GitHub, Hugging Face, and build.nvidia.com.
With the quantum computing market projected to exceed $11 billion by 2030, NVIDIA’s Ising launch aims to address the two biggest barriers to useful quantum applications: precise calibration and effective error correction.