NVIDIA Ising Calibration 1

MoE VLM for automated quantum processor calibration. Analyzes quantum measurement plots and infers tuning adjustments, reducing calibration time from days to hours.

Model Specifications

ArchitectureSCIENCE

Parameters35B

Familyising

VRAM (Q4)17.5GB

Mixture of ExpertsActive inference parameters: 3B.

Released April 14, 2026. Based on Qwen3.5-35B-A3B. Requires 2x L40S or 1x H100 minimum. Outperforms GPT-5.4 on QCalEval quantum benchmark.

#nvidia#quantum#science#vlm#moe#specializedSource

Share this Model

Send this model's specs directly to your community.

Post

Similar Models

NVIDIA Ising Decoder (Surface Code)

0.0018B

Ultra-lightweight 3D CNN (~1.8M params) for real-time quantum error correction using surface codes. Designed for integration into quantum control systems.

ESM3 Open

98B

Simulate & generate biology

ECMWF AIFS

Operational AI weather forecasting

Related Guides

How much VRAM do you really need?

A complete breakdown of quantization levels and VRAM overhead for running local models.

Best GPUs for Machine Learning in 2026

Comparing NVIDIA and AMD options for the best speed-to-dollar ratio.

GGUF vs EXL2 vs AWQ

Understanding local AI formats and which one to pick for your specific hardware.