NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning

Summary

NVIDIA Ising Calibration is an open-source vision language model designed to interpret quantum processor diagnostic outputs and recommend tuning steps. The newly released Ising Calibration 1.5 features a 31-billion-parameter architecture that is 11.4% smaller at BF16 precision than its predecessor. Trained on multi-modality partner data including superconducting qubits, quantum dots, ions, neutral atoms, and electrons on Helium, the model supports both zero-shot reasoning and in-context learning. Evaluated on the QCalEval benchmark, it scores 10% higher on average than comparable open models in zero-shot tasks and improves in-context learning performance by over 86% relative to the prior release. In addition to BF16 weights, the model offers an NVFP4 quantization option suitable for deployment on single consumer GPUs or NVIDIA DGX Spark hardware.

Takeaways

1. 1

   Ising Calibration 1.5 is an open-source 31B vision language model that is 11.4% smaller at BF16 precision than the previous version.

2. 2

   On the QCalEval benchmark, the model achieves a 10% average improvement over comparable open models in zero-shot evaluations and an 86.68% boost in in-context learning over its predecessor.

3. 3

   An NVFP4-quantized release enables deployment on single consumer GPUs or NVIDIA DGX Spark systems with high token throughput and minimal accuracy loss.