The NVIDIA Ising Calibration 1 NIM houses the NVIDIA-Ising-Calibration-1-35B-A3B-BF16 model, which is a purpose-built Mixture-of-Experts vision-language model (MoE VLM) built on Qwen3.5-35B-A3B,
NVIDIA Ising Calibration 1 NIM Overview
Description
The NVIDIA Ising Calibration 1 NIM houses the NVIDIA-Ising-Calibration-1-35B-A3B-BF16 model, which is a purpose-built Mixture-of-Experts vision-language model (MoE VLM) built on Qwen3.5-35B-A3B, specialized for analyzing quantum computing calibration experiment plots. The model accepts calibration experiment plot images and generates structured analytical outputs including technical descriptions, experimental conclusions, significance assessments, fit quality evaluations, parameter extractions, and experiment success classifications.
The model is intended for research and demonstration in quantum calibration analysis pipelines. Model outputs should be validated by domain experts before acting on experimental conclusions.
The container components are ready for commercial/non-commercial use.
License/Terms of Use:
The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products. Use of this model is governed by the NVIDIA Open Model License Agreement.
Governing Terms:
The Ising-Calibration-1-35B-A3B is governed by the NVIDIA Open Model License Agreement. If you download the software and materials as available from NVIDIA, use of the software is governed by the Apache License, Version 2.0.
ADDITIONAL INFORMATION: For Qwen3.5-35B-A3B Apache License, Version 2.0.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography: Global
Release Date: [NGC]
Build.Nvidia.com [04/14/2026] via [https://build.nvidia.com/nvidia/ising-calibration-1-35b-a3b]
NGC [04/14/2026] via [https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/ising-calibration-1-35b-a3b]
Program Classes:
The NVIDIA Ising Calibration 1 NIM Container includes the following model:
| Model Name | Use Case | How to Pull the Model |
|---|---|---|
| nvidia/NVIDIA-Ising-Calibration-1-35B-A3B-BF16 | Quantum calibration experiment image classification and analysis | Automatic |
Deployment Details:
The NIM is deployed as a Docker container exposing an OpenAI-compatible HTTP API on port 8000.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Reference(s):
- Qwen3.5 MoE architecture — Qwen Team, 2026
- QCalEval benchmark dataset for quantum calibration experiment evaluation
- vLLM inference engine for high-throughput serving
Container Version(s):
| Version | Precision | Description |
|---|---|---|
| nvidia/NVIDIA-Ising-Calibration-1:1.0.0 | BF16 | Production deployment, full-precision weights |
Software Stack:
| Component | Version |
|---|---|
| NIM Version | 1.0.0 |
| NIMTools | 1.9.0 |
| Base Image | nvcr.io/nim/qwen/qwen3.5-35b-a3b:1.7.0-variant |
| Backend | vLLM |
| CUDA | 13.0 |
| PyTorch | 2.10.0 |
Model Specifications:
| Property | Value |
|---|---|
| Architecture | Qwen3.5 MoE (Mixture of Experts) |
| Total Parameters | 35B (3B active per token) |
| Precision | BF16 (bfloat16) |
| Max Context Length | 262,144 tokens |
| Tensor Parallelism | 1 or 2 |
| Pipeline Parallelism | 1 |
Hardware Support Matrix
Hardware systems that have undergone QA testing:
| GPU | GPU Memory (GB) | Precision | # of GPUs | Disk Space (GB) |
|---|---|---|---|---|
| L40S | 48 | BF16 | 2 | 72 |
| H200 SXM | 141 | BF16 | 1 or 2 | 72 |
| GH200 | 96/144 | BF16 | 1 or 2 | 72 |
| B200 | 192 | BF16 | 1 or 2 | 72 |
| GB200 | 192 | BF16 | 1 or 2 | 72 |
| GB300 | 288 | BF16 | 1 | 72 |
| DGX Spark | 128 | BF16 | 1 | 72 |
Requires NVIDIA Hopper or NVIDIA Blackwell architecture.
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations:
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 internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more.
NVIDIA Developer Community Forum
Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NVIDIA NIM documentation for release documentation, deployment guides and more.
NVIDIA Developer Community Forum
For support, visit the NVIDIA Developer Community Forum.