NVIDIA NIM for GPU accelerated GPT-OSS-20B Model inference through OpenAI compatible APIs
GPT-OSS-20B Overview
Description:
This container houses the GPT-OSS-20B from OpenAI’s gpt‑oss family, an open‑weight 20B‑parameter Mixture‑of‑Experts (MoE) model designed for powerful reasoning, agentic tasks, and versatile developer use cases. Designed as a Mixture-of-Experts (MoE) model, structurally identical to the larger 117B variant, albeit with different hyperparameters. This model leverages SwiGLU activations and incorporates learned attention sinks within its architecture. Functionally, it serves as a robust reasoning model, supporting advanced capabilities such as chain-of-thought processing, adjustable reasoning effort levels, instruction following, and tool use. It operates strictly with text-only modalities for both input and output. A key strategic benefit is its suitability for enterprises and governments, facilitating on-premises or private cloud deployment to ensure enhanced data security and privacy.
The container components are ready for commercial/non-commercial use.
Documentation
Visit the LLM NIM documentation page for release documentation, deployment guides, and more.
Third-Party Community Consideration
The model embedded in the container 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 (https://huggingface.co/openai/gpt-oss-20b).
License/Terms of Use:
The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
The use of any models in this container is governed by the NVIDIA Open Model Agreement in addition to any terms which govern the specific models used.
You are responsible for ensuring that your use of any provided models complies with all applicable laws.
This model is released under the NVIDIA Open Model Agreement. The underlying model is licensed under the Apache License version 2.0.
Deployment Geography:
Global
Release Date:
Build.Nvidia.com 08/05/2025 via
GTP-OSS-20B Model by OpenAI | NVIDIA NIM
Huggingface 08/05/2025 via
https://huggingface.co/openai/gpt-oss-20b
GPT-OSS-20B
GPT-OSS-20B Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| GPT-OSS-20B | A model designed for powerful reasoning, agentic tasks, and versatile developer use cases. | Automatic |
Deployment Details:
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.
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 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/)
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.