A deployable inference container for serving a 30B dense multimodal causal language model with a perception encoder through industry-standard APIs.
Muse Glimmer NIM Overview
Description
A deployable inference container for serving Muse Glimmer, a 30B vision-language model (VLM) with a dense multimodal causal language architecture and a dedicated perception encoder, through industry-standard APIs. It supports local, always-on agentic workflows on NVIDIA GPU-accelerated systems, accepting interleaved text and image inputs to produce text output without requiring cloud infrastructure or network access.
For video workflows, applications should submit individual video frames as image inputs; the embedded VLM is not explicitly optimized for native temporal video understanding.
The container components are ready for commercial or non-commercial use.
Third-Party Community Consideration
The model embedded in the container is not owned or developed by NVIDIA. This model was developed and built to a third party's requirements for this application and use case. See the non-NVIDIA Muse Glimmer Model Card.
License and Terms of Use
GOVERNING DOWNLOAD TERMS: Use of this container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
You are responsible for ensuring that your use of NVIDIA-provided models complies with all applicable laws.
Deployment Geography
Global
Release Date
- NGC: August 10, 2026
Program Classes
The NIM container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Muse Glimmer | Local agentic workflows with multimodal input and text output | Automatic (embedded in container) |
Deployment Details
The NIM container exposes industry-standard inference APIs for integration into applications and workflows.
API Endpoints
/v1/chat/completions— Chat completions/v1/models— List available models/health/ready— Health check
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA hardware, such as GPU cores, and software frameworks, such as CUDA libraries, the model achieves faster training and inference times compared with CPU-only solutions.
References
Container Version(s)
2.1.4-variant
Security Common Vulnerabilities and Exposures (CVEs)
Review the Security Scanning tab on NGC for 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. VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and has established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal development teams to ensure these software components meet the requirements of the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities, or NVIDIA AI concerns.
Get Help
Getting Started with the NIM
Deploying and integrating the NIM is straightforward through industry-standard APIs. Visit the NVIDIA NIM for LLM and VLM documentation for release documentation, deployment guides, and more.
NVIDIA Developer Community Forum
Access community knowledge-base articles and support through the NVIDIA Developer Forums.