NVIDIA NIM for GPU accelerated Qwen3-Next-80B-A3B inference through OpenAI compatible APIs
Qwen3-Next-80B-A3B-Thinking Overview
This container houses the Qwen3-Next-80B-A3B-Thinking model, which is a text-generation Large Language Model. It is a hybrid Mixture-of-Experts (MoE) architecture that combines full attention layers with linear attention layers (Gated Delta Attention, a modified Mamba2 variant). The model consists of 48 layers and has approximately 80 billion total parameters, with 3.9 billion active parameters during inference.
The container components are ready for commercial/non-commercial use.
Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA Qwen3-Next-80B-A3B-Thinking Model Card
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the [NVIDIA Software License Agreement and Product-Specific Terms for AI Products]https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/). Use of this model is governed by the NVIDIA Community Model License. ADDITIONAL INFORMATION: Apache 2.0 License.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography:
Global
Release Date:
Build.NVIDIA.com 9/11/25 via link
Huggingface 9/11/25 via link
Program Classes:
This container houses the Qwen3-Next-80B-A3B-Thinking model.
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Qwen3-Next-80B-A3B-Thinking | A hybrid Mixture-of-Experts (MoE) architecture that combines full attention layers with linear attention layers . | Automatic |
Deployment Details:
Visit the NIM Container LLM page for release documentation, deployment guides, and more.
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.
Get Help
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.
Container Version(s):
Qwen3-Next-80B-A3B-Thinking-1.0
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 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.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.