NVIDIA NIM for GPU accelerated DeepSeek-V3.2-Exp inference through OpenAI compatible APIs
DeepSeek-V3.2-Exp Overview
Description:
This container houses the DeepSeek-V3.2-Exp, an experimental large language model optimized for text generation, reasoning, coding, and agentic tool use. As an intermediate step toward the next-generation architecture, V3.2-Exp builds upon V3.1-Terminus by introducing DeepSeek Sparse Attention (DSA)—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios. DSA achieves fine-grained sparse attention for the first time, delivering substantial improvements in long-context training and inference efficiency while maintaining virtually identical model output quality.
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 deepseek-ai/DeepSeek-V3.2-Exp.
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products; and the use of the model is governed by the NVIDIA Open Model License Agreement.
ADDITIONAL INFORMATION: MIT License.
Get Help
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography:
Global
Release Date:
catalog.ngc.nvidia.com: January 29, 2026 via link
Hugging Face: November 17, 2025 via
https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| DeepSeek-V3.2-Exp | Used for research and validation purposes in advanced text generation, reasoning, complex code generation, and sophisticated agentic workflows (e.g., Code Agent, Search Agent). As an experimental release, it explores more efficient transformer architectures for improved computational efficiency when processing extended text sequences. | 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.
Supported Hardware:
- NVIDIA Blackwell (B200)
- NVIDIA Hopper (H200)
- AMD MI350
- NPUs (A2, A3)
Runtime Engines:
- SGLang
- vLLM
Reference(s):
https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
Container Version(s):
DeepSeek-V3.2-Exp-1.0.0-Experimental
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 security vulnerabilities or NVIDIA AI Concerns here.
You are responsible for ensuring that your use of NVIDIA provided Models complies with all applicable laws.