1. [Home ](/) NVIDIA Ising # NVIDIA Ising NVIDIA Ising is a model family, training framework, and cookbook for building and deploying AI for [quantum computing](https://www.nvidia.com/en-us/glossary/quantum-computing/). Leveraging NVIDIA Ising enables quantum computing experts to get the full value of state-of-the-art artificial intelligence technology without requiring machine learning domain expertise. It solves existential blockers and scales useful quantum computing with the best classical computing has to offer. [Explore Models](https://huggingface.co/collections/nvidia/nvidia-ising "Explore Models")[Support](https://github.com/NVIDIA/ising "Support") * * * ## NVIDIA Ising Models The NVIDIA Ising model family gives quantum computer builders, operators, and developers the AI tools required to scale devices to fault tolerance. Key challenges on that path include calibration and quantum error correction. The new Ising vision language model for quantum calibration can be leveraged in an agentic workflow to automate quantum processor bring-up and retune calibration workflows. [Quantum error correction](https://www.nvidia.com/en-us/glossary/quantum-error-correction/) decoders need to be low latency while improving the logical error rate (LER) of the quantum processor they are connected to. Until now, machine learning pre-decoders capable of simultaneously reducing end-to-end latency, improving the LER, and scaling across both space and time to enable efficient lattice surgery operations have not been available. 3D CNN model architectures are key to supporting this capability, and NVIDIA Ising includes a fast, accurate model for SurfaceCode and ColorCode with off-the-shelf noise models. ### Ising Calibration 1.5 Calibration 1.5 is 3.27% better than Gemini 3.1 Pro, 9.68% better than Claude Opus 4.6, and 14.5% better than GPT 5.4. [Experience the Model as NVIDIA NIM™ API](https://build.nvidia.com/nvidia/ising-calibration-1.5-31b/playground) [Download the Model on Hugging Face](https://huggingface.co/nvidia/Ising-Calibration-1.5-31B-BF16) ### Ising Decoder SurfaceCode 1 Fast Decoder SurfaceCode 1 Fast offers 2.5x faster latency and 1.1x higher accuracy than PyMatching for d=13, p=0.003. [Download the Model on Hugging Face](https://huggingface.co/nvidia/Ising-Decoder-SurfaceCode-1-912K) ### Ising Decoder ColorCode 1 Fast Decoder ColorCode 1 offers 7x faster latency and 347x higher accuracy than Chromobius for d=31, p=0.003. [Download the Model on Hugging Face](https://huggingface.co/nvidia/Ising-Decoder-ColorCode-1-Fast) * * * ## NVIDIA Ising Calibration and Ising Decoding NVIDIA Ising Decoding includes a training pipeline for decoder models so you can train your own decoders and custom tailor them to their quantum computer noise models for the best performance. Examples are included for real-time decoding with the models, along with scripts to quantize. NVIDIA Ising Calibration offers an agentic workflow to enable out-of-the-box ease of use with Ising Calibration 1.5. Learn how to deploy the model with an agent or integrate with your QPU. Use examples for fine-tuning the models with your own data and the QCalEval benchmark and data to test model effectiveness. ### Ising Calibration Run the Ising Calibration 1.5 in an agentic workflow with our example on GitHub. Evaluate your own models with our QCalEval benchmark dataset. [Run With an Agent on GitHub](https://github.com/NVIDIA/Quantum-Calibration-Agent-Blueprint/) [Download the NVIDIA NIM Container](https://catalog.ngc.nvidia.com/orgs/nim/nvidia/containers/ising-calibration-1-5-31b/-?_lr=1) [Read the Benchmark Paper](https://research.nvidia.com/publication/2026-04_qcaleval-benchmarking-vision-language-models-quantum-calibration-plot) ### Ising Decoding Leverage cuQuantum cuStabilizer and PyTorch to efficiently train state-of-the-art models for your specific QPU data, wherever you need. [Run Real-Time Decoding With NVIDIA CUDA-Q™ QEC](https://nvidia.github.io/cudaqx/examples_rst/qec/realtime_predecoder_pymatching.html) [Download the Training Pipeline on GitHub](https://github.com/NVIDIA/Ising-Decoding) [Read the Surface Code Model Architecture Paper](https://research.nvidia.com/publication/2026-04_fast-ai-based-pre-decoders-surface-codes) [Read the Color Code Model Architecture Paper](https://research.nvidia.com/publication/2026-07_fast-and-accurate-ai-based-pre-decoders-color-codes) * * * ## Get Started With NVIDIA Ising Start deploying AI models for quantum computing workloads. Explore real-time inference and agentic workflows with real quantum computer data. ![icon representing workflows](https://developer.download.nvidia.com/images/ising/m48-quantum-calibration.svg) ### Run a Quantum Calibration Agent Learn how to deploy a quantum calibration agent, input your experiment workflow, and let the agent manage the VLM to evaluate experimental results. [ Review the Tutorial ](https://github.com/NVIDIA/Quantum-Calibration-Agent-Blueprint/) ![icon representing workflows](https://developer.download.nvidia.com/images/ising/m48-quantum-error-correction.svg) ### Train Real-Time Decoders In this self-paced tutorial, learn how to train a pre-decoder specific to your noise model, designed for real-time decoding workflows. [ Review the Tutorial ](https://github.com/NVIDIA/Ising-Decoding/blob/main/cookbook/predecoder.ipynb) * * * ## NVIDIA Ising Learning Library The rows below are the raw result records for this component — one row per record. Column names are the source index fields; the full data is also downloadable in the links that follow. | title | featured | x_formats | document_url | technologies | document_date | short_summary | document_title | learning_level | x_content_types | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Leverage Quantum Enhanced Optimization to Solve the LABS Problem | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/hybrid-workflows/01_quantum_enhanced_optimization_LABS.ipynb | CUDA-Q | 2026-02-19T19:42:59.000Z | Build hybrid quantum-classical workflows for radar signal optimization using CUDA-Q. | Leverage Quantum Enhanced Optimization to Solve the LABS Problem | Technical - Intermediate | Tutorial | | Compile Quantum Circuits with Diffusion Models | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/ai-for-quantum/01_compiling_unitaries_using_diffusion_models.ipynb | CUDA-Q, PyTorch | 2026-01-27T17:48:03.000Z | Implement AI-driven quantum circuit synthesis using diffusion models with CUDA-Q. | Compile Quantum Circuits with Diffusion Models | Technical - Intermediate | Tutorial | | VQE & GQE for Molecular Ground States | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/chemistry-simulations/vqe_and_gqe.ipynb | CUDA-Q, CUDA-Q Solvers | 2026-01-29T15:12:39.000Z | Apply VQE and the Generative Quantum Eigensolver for predicting molecular ground state energy. | VQE & GQE for Molecular Ground States | Technical - Intermediate | Tutorial | | Optimize Portfolios with Three Quantum Approaches | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/quantum-applications-to-finance/03_qchop.ipynb | CUDA-Q | 2026-01-22T15:36:27.000Z | Solve portfolio optimization using QAOA, quantum annealing, and Q-Chop. | Optimize Portfolios with Three Quantum Approaches | Technical - Intermediate | Tutorial | | Solving the MaxCut Problem with Divide-and-Conquer QAQA | false | hands-on | https://nvidia.github.io/cuda-q-academic/learningpath.html?track=track-qaoa | CUDA-Q | 2026-02-05T18:48:37.000Z | Implement QAOA for graph optimization with circuit cutting and parallel computation. | Solving the MaxCut Problem with Divide-and-Conquer QAQA | Technical - Intermediate | Learning-path | | Build Quantum Error Correction Decoders | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/qec101/04_QEC_Decoders.ipynb | CUDA-Q, CUDA-Q QEC, cuQuantum, PyTorch | 2026-02-27T13:58:59.000Z | Build and understand QEC decoders including AI-based and belief propagation methods. | Build Quantum Error Correction Decoders | Technical - Intermediate | Tutorial | | QEC 101: Error Correction Learning Path | true | hands-on | https://nvidia.github.io/cuda-q-academic/learningpath.html?track=track-qec | CUDA-Q, CUDA-Q QEC, cuQuantum | 2026-02-27T13:58:59.000Z | Master quantum error correction from stabilizer codes to topological codes. | QEC 101: Error Correction Learning Path | Technical - Intermediate | Learning-path | | Parallelize ADAPT-VQE Across GPUs | false | hands-on | https://github.com/NVIDIA/cuda-q-academic/blob/main/chemistry-simulations/adapt_vqe.ipynb | CUDA-Q, CUDA-Q Solvers | 2026-01-27T17:48:03.000Z | Implement and parallelize ADAPT-VQE across multiple QPUs using CUDA-Q. | Parallelize ADAPT-VQE Across GPUs | Technical - Advanced | Tutorial | | Quick Start: Quantum Computing with CUDA-Q | true | hands-on | https://nvidia.github.io/cuda-q-academic/learningpath.html?track=track-quickstart | CUDA-Q | 2026-02-13T21:11:41.000Z | Progress from quantum basics to hybrid variational algorithms with CUDA-Q. | Quick Start: Quantum Computing with CUDA-Q | Technical - Beginner | Learning-path | | cuQuantum Integrations in QuTiP & scQubits | false | blog | https://developer.nvidia.com/blog/accelerate-qubit-research-with-nvidia-cuquantum-integrations-in-qutip-and-scqubits/ | CUDA-Q, cuQuantum | 2025-10-14T04:00:00.000Z | GPU-accelerate QPU-design simulations using cuQuantum integrations in QuTiP and scQubits. | cuQuantum Integrations in QuTiP & scQubits | Technical - Intermediate | Explainer | | Realtime AI Predecoder Pipeline with CUDA-QX and PyMatching | false | webpage | https://nvidia.github.io/cudaqx/examples_rst/qec/realtime_predecoder_pymatching.html | CUDA-Q, CUDA-Q QEC, Ising | 2026-04-14T04:00:00.000Z | Build a real-time AI predecoder pipeline using TensorRT and PyMatching. | Realtime AI Predecoder Pipeline with CUDA-QX and PyMatching | Technical - Intermediate | Tutorial | | Ising-Decoding README: Setup, Configuration, and Usage Guide | false | webpage | https://github.com/NVIDIA/Ising-Decoding/blob/main/README.md | CUDA-Q QEC, Ising | 2026-04-13T04:00:00.000Z | Configure and run the Ising pre-decoder training and inference workflows. | Ising-Decoding README: Setup, Configuration, and Usage Guide | Technical - Intermediate | Documentation | | Ising-Decoding: A Training Framework for AI Quantum Error Correction Decoders | false | code | https://github.com/NVIDIA/Ising-Decoding | CUDA-Q QEC, Ising | 2026-04-14T04:00:00.000Z | Build and deploy scalable AI-based quantum error correction decoders. | Ising-Decoding: A Training Framework for AI Quantum Error Correction Decoders | Technical - Intermediate | Samples | | NVIDIA Ising: A Model Family Accelerating the Development of Useful Quantum Computers | false | code | https://github.com/NVIDIA/ising | Ising | 2026-04-14T04:00:00.000Z | Explore the NVIDIA Ising model family for quantum calibration and error correction. | NVIDIA Ising: A Model Family Accelerating the Development of Useful Quantum Computers | Technical - Beginner | Documentation | | Ising-Decoder-SurfaceCode-1-Fast: Lightweight AI Pre-Decoder for QEC | false | code | https://huggingface.co/nvidia/Ising-Decoder-SurfaceCode-1-Fast | Ising | 2026-04-14T04:00:00.000Z | Download the fast Ising pre-decoder model for surface code error correction. | Ising-Decoder-SurfaceCode-1-Fast: Lightweight AI Pre-Decoder for QEC | Technical - Intermediate | Samples | | Ising-Calibration-1-35B-A3B: Quantum Calibration Vision-Language Model | false | code | https://huggingface.co/nvidia/Ising-Calibration-1-35B-A3B | Ising | 2026-04-14T04:00:00.000Z | Download and run the Ising Calibration MoE VLM for quantum experiment analysis. | Ising-Calibration-1-35B-A3B: Quantum Calibration Vision-Language Model | Technical - Intermediate | Samples | | NVIDIA Ising Pre-Decoder Tutorial Notebook | false | hands-on | https://github.com/NVIDIA/Ising-Decoding/blob/main/cookbook/predecoder.ipynb | Ising | 2026-04-13T04:00:00.000Z | Train and evaluate an AI pre-decoder for quantum error correction step by step. | NVIDIA Ising Pre-Decoder Tutorial Notebook | Technical - Intermediate | Tutorial | | Deploy Ising Calibration 1 NIM Locally | true | code | https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/ising-calibration-1-35b-a3b?version=1.0.2 | Ising | 2026-05-19T00:00:00.000Z | Download the NVIDIA NIM container for Ising Calibration 1 | Deploy Ising Calibration 1 NIM Locally | Technical - Intermediate | Samples | | Build a Real-Time AI Predecoder Pipeline Using TensorRT and PyMatching | false | blog | https://developer.nvidia.com/blog/real-time-decoding-algorithmic-gpu-decoders-and-ai-inference-enhancements-in-nvidia-cuda-q-qec/ | CUDA-Q, CUDA-Q QEC, cuQuantum | 2025-12-14T00:00:00.000Z | Accelerate quantum error correct research by applying GPU-accelerated decoders to quantum processors. | Build a Real-Time AI Predecoder Pipeline Using TensorRT and PyMatching | Technical - Intermediate | Explainer | | NVIDIA Ising Introduces AI-Powered Workflows to Build Fault-Tolerant Quantum Systems | true | blog | https://developer.nvidia.com/blog/nvidia-ising-introduces-ai-powered-workflows-to-build-fault-tolerant-quantum-systems/ | Ising | 2026-04-14T04:00:00.000Z | Explore AI-powered workflows for building fault-tolerant quantum computing systems. | NVIDIA Ising Introduces AI-Powered Workflows to Build Fault-Tolerant Quantum Systems | Technical - Beginner | Explainer | | CUDA-Q Application Hub | true | code | https://nvidia.github.io/cuda-quantum/latest/using/applications.html | CUDA-Q | 2026-04-17T00:00:00.000Z | Run Python notebooks of real-life applications showing the power of CUDA-Q. | CUDA-Q Application Hub | Technical - Intermediate | Tutorial | | CUDA-Q Documentation | true | webpage | https://nvidia.github.io/cuda-quantum/latest/index.html  | CUDA-Q | 2026-04-16T00:00:00.000Z | Browse documentation for the latest version of CUDA-Q. | CUDA-Q Documentation | Technical - Intermediate | Documentation | | CUDA-QX | true | webpage | https://nvidia.github.io/cudaqx/index.html | CUDA-Q | 2026-04-17T00:00:00.000Z | Explore domain-specific CUDA-Q libraries for QEC and solvers. | CUDA-QX | Technical - Intermediate | Documentation | | Simulating Quantum Dynamics with CUDA-Q Learning PAth | false | hands-on | https://nvidia.github.io/cuda-q-academic/learningpath.html?track=track-dynamics | CUDA-Q, cuQuantum | 2026-02-22T20:20:19.000Z | Simulate quantum dynamics using GPU-accelerated Schrödinger and Lindblad equations. | Simulating Quantum Dynamics with CUDA-Q Learning PAth | Technical - Intermediate | Learning-path | | Ising-Decoder-SurfaceCode-1-Accurate: High-Fidelity AI Pre-Decoder for QEC | false | code | https://huggingface.co/nvidia/Ising-Decoder-SurfaceCode-1-Accurate | Ising | 2026-04-14T04:00:00.000Z | Download the accurate Ising pre-decoder model for surface code error correction. | Ising-Decoder-SurfaceCode-1-Accurate: High-Fidelity AI Pre-Decoder for QEC | Technical - Intermediate | Samples | | QCalEval: Benchmark Dataset for Quantum Calibration Vision-Language Models | false | code | https://huggingface.co/datasets/nvidia/QCalEval | Ising | 2026-04-14T04:00:00.000Z | Download the QCalEval benchmark dataset for evaluating quantum calibration VLMs. | QCalEval: Benchmark Dataset for Quantum Calibration Vision-Language Models | Technical - Intermediate | Samples | | Simulating Chemical Systems with CUDA-Q | false | hands-on | https://nvidia.github.io/cuda-q-academic/learningpath.html?track=track-chem | CUDA-Q, CUDA-Q Solvers, cuQuantum | 2026-02-05T16:52:24.000Z | Explore quantum chemistry techniques from VQE to QM/MM frameworks. | Simulating Chemical Systems with CUDA-Q | Technical - Intermediate | Learning-path | [Download the raw results data (JSON)](https://developer.nvidia.com/search-data/quantum_computing.json) * * * ## More Resources ![Decorative image representing Community](https://developer.download.nvidia.com/icons/m48-people-group.svg) ### NVIDIA GitHub Issues ![Decorative image representing Developer Program](https://developer.download.nvidia.com/icons/m48-developer-1.svg) ### Try NVIDIA Ising Models ![Decorative image representing Developer Newsletter](https://developer.download.nvidia.com/icons/m48-email-settings.svg) ### Sign Up for Developer Newsletter * * * ## Ethical AI NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). Get started with NVIDIA Ising today. [Learn More](https://github.com/NVIDIA/ising)