-

Penguin Solutions Expands ComputeAI Portfolio with NVIDIA Vera Rubin NVL72 Rack-Scale Systems

Pre-validated, liquid-cooled rack-scale system simplifies deployment, reduces integration complexity and accelerates time to value for next-generation AI workloads.

FREMONT, Calif.--(BUSINESS WIRE)--Penguin Solutions, Inc. (Nasdaq: PENG), the AI Factory Platform Company, today announced the availability of ComputeAI™ NML72-VR200, a pre-validated, liquid-cooled rack-scale platform built on the NVIDIA Vera Rubin NVL72 architecture. The system provides a deployment-ready foundation for advanced AI workloads, including agentic AI, inference-time scaling, and gigascale model development, supporting AI cloud providers, enterprises, and sovereign AI initiatives.

As AI workloads grow in scale and complexity, particularly agentic AI systems that execute multi-step tasks and reason across large context windows, organizations require greater compute density, memory capacity, networking performance, and power and cooling capabilities. Building infrastructure to meet these requirements from smaller systems increases integration complexity, extends deployment timelines, and delays time to production.

Penguin Solutions' ComputeAI NML72-VR200 addresses these challenges with a fully integrated, pre-validated rack-scale system featuring 72 NVIDIA Rubin GPUs, 36 NVIDIA Vera CPUs, sixth-generation NVIDIA NVLink, NVIDIA ConnectX-9 networking, NVIDIA BlueField-4 DPUs, high-capacity memory and storage, rack-level power, and direct liquid cooling. This integrated architecture simplifies deployment, reduces integration risk, and provides a repeatable foundation for scaling AI services and proprietary model development.

“As AI workloads grow more complex, organizations need infrastructure that can move from deployment to production quickly without compromising performance or scalability,” said Ranjeet Sudan, Vice President of Product Management at Penguin Solutions. “With the ComputeAI NML72-VR200, we combine advanced NVIDIA technology with Penguin Solutions' deep infrastructure expertise to deliver a pre-validated rack-scale system that simplifies deployment and enables customers to scale next-generation AI workloads with greater speed and confidence.”

Designed to support demanding AI workloads, including high-concurrency agentic applications, long-context reasoning, and large-scale model training, ComputeAI NML72-VR200 expands Penguin Solutions' ComputeAI portfolio of advanced compute systems optimized for AI data centers. As part of the company's Full-Stack AI Factory Platform, the solution combines advanced compute technologies with Penguin Solutions' infrastructure expertise to help organizations simplify deployment, scale operations and maximize the value of their AI investments.

ComputeAI NML72-VR200 is available now. To learn more, click here.

Penguin Solutions and ComputeAI are trademarks or registered trademarks of Penguin Solutions, Inc. or its affiliates. All other trademarks are the property of their respective owners.

About Penguin Solutions

Penguin Solutions is the AI Factory Platform Company. We design, build, and manage next-generation data centers for enterprises, sovereign AI initiatives, and AI cloud providers.

With deep design expertise at the intersection of data center AI infrastructure and memory solutions, our Full-Stack AI Factory Platform combines differentiated infrastructure software, advanced memory, compute systems, end-to-end services, and industry-leading partner technologies to help customers accelerate deployment, optimize token economics, and maximize the return on their AI investments.

Learn more at PenguinSolutions.com.

Contacts

Media Relations
Lerin O’Neill
Sr. Director, Corporate Communications & Public Relations
Penguin Solutions
pr@penguinsolutions.com

Penguin Solutions, Inc.

NASDAQ:PENG
Details
Headquarters: Fremont, California USA
CEO: Kash Shaikh
Employees: 2765
Organization: PUB
Revenues: $1.73B (2026)

Release Versions

Contacts

Media Relations
Lerin O’Neill
Sr. Director, Corporate Communications & Public Relations
Penguin Solutions
pr@penguinsolutions.com

More News From Penguin Solutions, Inc.

Penguin Solutions Expands ClusterWareAI Capabilities to Accelerate Deployment and Scaling of NVIDIA Vera Rubin Platform

FREMONT, Calif.--(BUSINESS WIRE)--Penguin Solutions, Inc. (Nasdaq: PENG), the AI Factory Platform Company, today announced the latest release of its ClusterWareAI™ AI factory platform operating system software. With rapid provisioning and scaling capabilities for the NVIDIA Vera Rubin platform, this update enables enterprises and AI cloud providers to quickly deploy the latest NVIDIA POD-scale systems for agentic AI and reasoning. Penguin Solutions ClusterWareAI software provides intelligent cl...

Penguin Solutions Unveils Industry’s First Photonics-Based HBM-Class Memory Appliance to Break the GPU Memory Wall for Agentic AI

FREMONT, Calif.--(BUSINESS WIRE)--Penguin Solutions, Inc. (Nasdaq: PENG), the AI Factory Platform Company, today unveiled the MemoryAI™ Photonic Appliance, the industry’s first photonics-based HBM-class memory appliance designed to overcome GPU memory capacity constraints for agentic AI workloads. Using silicon photonics, the appliance is built to enable CPUs and GPUs to transparently share memory at high bandwidth memory (HBM)-class data rates. Penguin is showcasing the appliance at SC26 in Ch...

Penguin Solutions Introduces CXL-Enabled DDR4 Module to Help Address Memory Shortages in AI Data Centers

FREMONT, Calif.--(BUSINESS WIRE)--Penguin Solutions, Inc. (Nasdaq: PENG), the AI Factory Platform Company, today introduced the SMART CXL-8F2W-D4, an eight-DIMM DDR4 Compute Express Link® (CXL) memory add-in card that enables organizations to adapt DDR4 memory for use in AI systems. Using DDR4 as an alternative to newer-generation DDR5 memory provides an innovative approach offering performance, sourcing, and economic benefits for the buildout of AI infrastructure. According to TechInsights, In...
Back to Newsroom