NVIDIA Ising

### TL;DR

NVIDIA Ising is the world's first family of open-source AI models for quantum computing, designed to accelerate quantum processor calibration and quantum error correction. Named after the landmark Ising mathematical model, it delivers up to 2.5× faster and 3× more accurate quantum error correction decoding than the current open-source standard (pyMatching), and automates continuous processor calibration from days to hours.

Key Insights & Metrics

Key Features

• Ising Calibration — a vision language model that interprets measurements from quantum processors in real time, enabling AI agents to automate continuous calibration and reducing time needed from days to hours; adopted by IonQ, Atom Computing, Harvard, Fermi National Lab, and more
• Ising Decoding — two 3D CNN model variants (speed-optimized and accuracy-optimized) for real-time quantum error correction; up to 2.5× faster and 3× more accurate than pyMatching, the current open-source industry standard
• Fully open and customizable — models, tools, and training data available on GitHub, Hugging Face, and build.nvidia.com; integrates with NVIDIA CUDA-Q software platform and NVQLink QPU-GPU hardware interconnect; fine-tunable for specific hardware architectures

Discussion