Qwen3-Coder-Next NIM Container is the backend inference container for deploying the Qwen3-Coder-Next model (80B total parameters, 3B activated) via NVIDIA Inference Microservices description
Qwen3-Coder-Next NIM Container
Description
Qwen3-Coder-Next NIM Container is the backend inference container for deploying the Qwen3-Coder-Next model (80B total parameters, 3B activated) via NVIDIA Inference Microservices. This container provides optimized inference capabilities for coding agents and local development workloads, featuring support for vLLM, SGLang, and TensorRT-LLM acceleration engines with 262k context length support.
The container components are ready for commercial use.
Third-Party Community Consideration:
This container is built for a model not owned or developed by NVIDIA. The underlying model has been developed by Qwen (Alibaba Cloud) and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA Qwen3-Coder-Next Model Card.
License and Terms of Use:
GOVERNING TERMS: [The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for NVIDIA AI Products. Use of this model is governed by the NVIDIA Open Model License. Additional Information: Apache 2.0
Deployment Geography:
Deployment Geography: Global
Release Date:
NGC catalog.NVIDIA.com 02/18/2026 via link
Program Classes:
The Qwen3-Coder-Next NIM Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Qwen3-Coder-Next | AI-powered coding assistance and agentic workflows | Automatic (embedded in container) |
Deployment Details:
The Qwen3-Coder-Next NIM Container provides a production-ready inference service via standard HTTP and gRPC APIs. The container automatically downloads model weights from Hugging Face on first startup and exposes OpenAI-compatible API endpoints for seamless integration.
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):
References: Qwen3-Coder-Next HuggingFace Model Page, Qwen3-Coder GitHub Repository, Qwen Documentation, Qwen Blog - Qwen3-Coder-Next Announcement.
Container Version(s):
1.5.0-variant
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
NVIDIA Developer Community Forum
Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)