Supermicro Announces Support for Upcoming NVIDIA Vera Rubin NVL72, HGX Rubin NVL8 and Expanded Rack-Scale Manufacturing Capacity for Liquid-Cooled AI Solutions

Rhea-AI Summary

Supermicro (NASDAQ: SMCI) announced expanded US-based manufacturing capacity and enhanced liquid-cooling solutions to accelerate deployment of NVIDIA Vera Rubin NVL72 and NVIDIA HGX Rubin NVL8 platforms on Jan. 5, 2026.

The announcement highlights a rack-scale NVL72 SuperCluster with 72 Rubin GPUs, 36 Vera CPUs, 3.6 exaflops NVFP4, 1.4 PB/s HBM4 bandwidth, and advanced warm-water in-row CDU liquid-cooling. It also details a 2U HGX Rubin NVL8 8-GPU system delivering 400 petaflops NVFP4 and 176 TB/s HBM4 bandwidth. Supermicro positions its Data Center Building Block Solutions and Direct Liquid Cooling to enable faster, customizable, rack-scale AI deployments with NVIDIA interconnects and Spectrum-X networking options.

Positive

• Flagship NVL72 SuperCluster: 3.6 exaflops NVFP4
• NVL72 memory bandwidth: 1.4 PB/s HBM4
• HGX NVL8: 400 petaflops NVFP4 and 176 TB/s HBM4
• Supports NVIDIA NVLink 6 and BlueField-4 DPUs for rack-scale security
• Expanded US-based manufacturing to speed time-to-deployment
• Advanced Direct Liquid Cooling with in-row CDU warm-water operation

Negative

• No financial guidance, cost, or capacity figures disclosed for the expansion
• Manufacturing capacity increase not quantified as percent or absolute units
• Deployment depends on rack-scale liquid-cooling infrastructure adoption

Key Figures

Vera Rubin NVL72 scale 72 NVIDIA Rubin GPUs & 36 NVIDIA Vera CPUs NVIDIA Vera Rubin NVL72 SuperCluster configuration

NVL72 performance 3.6 exaflops NVFP4 NVIDIA Vera Rubin NVL72 system performance

NVL72 memory 1.4 PB/s HBM4 bandwidth; 75 TB memory NVIDIA Vera Rubin NVL72 memory subsystem

HGX Rubin NVL8 compute 400 petaflops NVFP4 2U liquid-cooled NVIDIA HGX Rubin NVL8 system

HGX Rubin NVL8 bandwidth 176 TB/s HBM4; 28.8 TB/s NVLink 2U NVIDIA HGX Rubin NVL8 memory/interconnect

ConnectX-9 networking 1600 Gb/s SuperNICs Networking in 2U NVIDIA HGX Rubin NVL8 systems

NVIDIA Vera CPU cores 88 cores / 176 threads NVIDIA Vera CPU specification

Spectrum-6 switching 102.4 Tb/s switching NVIDIA Spectrum-6 Ethernet ASIC for Spectrum-X networking

Market Reality Check

$30.16 Last Close

Volume Volume 36,280,123 vs 22,205,235 20-day average (relative volume 1.63) ahead of this AI hardware announcement. high

Technical Shares at $30.07, trading below the $42.23 200-day MA, despite positive next-gen NVIDIA Rubin platform news.

Peers on Argus

SMCI was down 2.87% pre-news while key hardware peers like HPQ (-2.04%), WDC (-2.74%), STX (-1.74%), PSTG (-0.83%), and LOGI (-1.33%) also traded lower, suggesting broader weakness but scanner data did not flag a unified sector momentum move.

Common Catalyst Peers had misc. CES- and earnings-related headlines, while SMCI’s news focuses on NVIDIA Rubin-based AI infrastructure and liquid cooling.

Historical Context

Date	Event	Sentiment	Move	Catalyst
Dec 31	Server product launch	Positive	-1.3%	Introduced high-density, liquid-cooled 6U SuperBlade with large core and memory scale.
Dec 11	AI infrastructure talks	Positive	-5.0%	Described role in early-stage GPU-based AI data center evaluations in the Philippines.
Dec 09	GPU systems launch	Positive	-0.3%	Announced new liquid-cooled NVIDIA HGX B300 systems with high GPU density and efficiency.
Dec 09	AI servers showcase	Positive	-1.0%	Showcased AI-optimized servers and edge systems, including NVIDIA HGX B300 and GB300 NVL72.
Nov 20	Investor conferences	Positive	-6.4%	Outlined participation in several December tech and AI investor conferences.

Pattern Detected

Recent news — largely product launches, AI initiatives, and investor events — has often been followed by negative 24h price moves, indicating a pattern of selling into news.

Recent Company History

Over the last few months, SMCI has repeatedly highlighted high-density, liquid-cooled infrastructure and AI-focused solutions. On Dec 31, 2025, it launched a 6U SuperBlade with up to 25,600 cores per rack. Earlier AI-related announcements around NVIDIA Blackwell systems and sovereign AI data centers also saw post-news declines. Participation in December investor conferences on Nov 20, 2025 similarly coincided with a negative reaction. Today’s NVIDIA Vera Rubin NVL72/NVL8 support continues this AI and liquid-cooling narrative.

Market Pulse Summary

This announcement underscores SMCI’s strategy to anchor itself in next-generation AI data centers through support for NVIDIA Vera Rubin NVL72 and HGX Rubin NVL8 platforms and advanced liquid cooling. It extends a series of AI-focused launches built on GPU-dense, energy-efficient architectures. Investors may track how quickly these rack-scale, liquid-cooled systems convert into revenue, alongside broader hardware trends and any subsequent filings or earnings updates that quantify adoption of these new platforms.

Key Terms

direct liquid cooling technical

"Advanced Direct Liquid Cooling (DLC) Technology with Supermicro US Based In-House..."

Direct liquid cooling is a method that removes heat from electronic components by bringing a coolant into close contact with the parts that generate heat, rather than relying on fans and air flow. For investors, it matters because it enables denser, more energy-efficient and potentially more reliable data centers or computing equipment—think of it as swapping a box fan for a targeted water jacket—lowering operating costs and supporting faster, higher-performance hardware.

nvidia nvlink 6 technical

"into a coherent platform with NVIDIA NVLink 6 and scales-out with NVIDIA Quantum-X800..."

A high-speed GPU-to-GPU communication link (the sixth-generation NVLink family) that lets graphics processors share large amounts of data much faster than standard connections. Like adding a multi-lane expressway between processors instead of a single local road, it reduces delays and enables bigger, faster computing tasks; investors watch it because adoption can drive demand for higher-margin hardware, support growth in data‑center and AI markets, and affect a maker’s competitive position and revenue potential.

dpu technical

"NVIDIA BlueField®-4 DPUs into a coherent platform with NVIDIA NVLink 6..."

Distributions per unit (DPU) is the amount of cash or income paid to each unit holder of a trust, real estate investment trust (REIT) or similar pooled investment for a given period. It tells investors how much cash income they received per unit, like getting a fixed slice of a pie for every share you own, and helps compare yield and judge whether the payout level is steady, growing or at risk.

mixture-of-experts models technical

"communication for the training and inference of massive mixture-of-experts models."

Mixture-of-experts models are a type of artificial intelligence that uses many small specialist “experts,” each trained to handle different kinds of tasks or data, and a gatekeeper that routes each input to the most suitable experts. For investors, they matter because this approach can deliver higher accuracy and faster results while using less computing power than one-size-fits-all models, affecting a company’s product performance, operating costs, and competitive position in AI-driven markets.

confidential computing technical

"3rd Generation Confidential Computing: Delivers rack-scale confidential computing..."

Confidential computing is a technology that keeps data secure while it is being processed or analyzed, even from the systems that run the calculations. Think of it like a locked box where sensitive information is kept safe inside, no matter what happens during the work. This helps protect private data from unauthorized access, making it especially important for businesses and investors concerned about data privacy and security.

serdes technical

"Spectrum-6 Ethernet ASIC (102.4 Tb/s switching on TSMC 3nm with 200G SerDes..."

SerDes (short for serializer/deserializer) is an electronic function that converts parallel streams of data into a single fast serial stream and then converts it back, like packing many lanes of traffic into one high-speed highway and unpacking them at the other end. Investors care because SerDes chips and blocks determine how quickly and efficiently devices, data centers and networks can move information; improvements or bottlenecks affect product performance, production costs, and demand across the semiconductor and communications supply chain.

co-packaged optics technical

"3nm with 200G SerDes co-packaged optics and fully shared buffers)."

Co-packaged optics are optical components—lasers and fiber interfaces—physically packaged together with a network switch’s main processing chip so light-based data links sit much closer to the chip instead of traveling over long electrical traces. For investors, this matters because it can dramatically cut power use, boost data speed and density, and lower system costs in large data centers and telecom equipment, much like moving a power outlet next to a heavy appliance to avoid long, inefficient extension cords.

data processing unit technical

"NVIDIA BlueField -4 DPU running a variety of data management solutions."

A data processing unit is a specialized chip or hardware component designed to handle heavy data tasks—such as moving, sorting, encrypting, or preparing information—so the main computer processors can focus elsewhere. Investors care because DPUs can lower operating costs, improve performance and security, and enable new cloud or data services; like a traffic controller that reduces jams, a DPU can make a company’s computing more efficient and competitively stronger.

AI-generated analysis. Not financial advice.

Data Center Building Block Solutions® (DCBBS) and Advanced Direct Liquid Cooling (DLC) Technology with Supermicro US Based In-House Design/Manufacturing Accelerate Time to Deployment of Next Generation Liquid-cooled AI Infrastructure

SAN JOSE, Calif., Jan. 5, 2026 /PRNewswire/ -- Supermicro, Inc. (NASDAQ: SMCI), a total IT solution provider for AI, cloud, storage, and 5G/edge, today announced expansions in manufacturing capacity and liquid-cooling capabilities, in collaboration with NVIDIA, to enable first-to-market delivery of data center-scale solutions optimized for the NVIDIA Vera Rubin and Rubin platforms. Leveraging accelerated development and collaboration with NVIDIA, Supermicro is uniquely positioned to rapidly deploy the flagship NVIDIA Vera Rubin NVL72 and NVIDIA HGX™ Rubin NVL8 systems. Supermicro's proven Data Center Building Block Solutions (DCBBS) approach delivers streamlined production, extensive customization options, and faster time-to-deployment, giving customers a decisive competitive edge in next-generation AI infrastructure.

"Supermicro's long-standing partnership with NVIDIA and our agile building block solutions enable us to bring the most advanced AI platforms to market faster than others," said Charles Liang, president and CEO of Supermicro. "With expanded manufacturing and industry-leading liquid-cooling expertise, we're empowering hyperscalers and enterprises to deploy the NVIDIA Vera Rubin and Rubin platforms infrastructure at scale with unmatched speed, efficiency, and reliability."

For more information, please visit https://www.supermicro.com/en/accelerators/nvidia/vera-rubin

Flagship Products:

• NVIDIA Vera Rubin NVL72 SuperCluster: the premier rack-scale system unifies 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs, NVIDIA ConnectX^®-9 SuperNICs, and NVIDIA BlueField^®-4 DPUs into a coherent platform with NVIDIA NVLink 6 and scales-out with NVIDIA Quantum-X800 InfiniBand and NVIDIA Spectrum-X Ethernet to power the AI industrial revolution. It delivers 3.6 exaflops NVFP4 performance, 1.4 PB/s HBM4 bandwidth, and 75 TB of fast memory. Built on the 3rd-generation NVIDIA MGX rack architecture for superior serviceability, reliability, and availability, Supermicro's implementation incorporates an enhanced data center-scale liquid-cooling technology stack with in-row Coolant Distribution Units (CDUs). This enables scalable warm-water cooling operation that minimizes energy consumption and water usage while maximizing density and efficiency.
• 2U Liquid-cooled NVIDIA HGX Rubin NVL8 Systems: this compact 8-GPU system is optimized for AI and HPC workloads, delivering breakthrough performance and efficiency to enterprises for intelligence at scale. It provides 400 petaflops NVFP4, 176 TB/s HBM4 bandwidth, 28.8 TB/s NVLink bandwidth, and 1600 Gb/s NVIDIA ConnectX-9 networking SuperNICs. Supermicro delivers rack-scale design with maximum deployment flexibility and configuration options supporting flagship x86 CPUs such as next-generation Intel® Xeon® or AMD EPYC™ processors. Available options include a high-density 2U busbar design for optimal rack integration featuring Supermicro's industry-leading advanced Direct Liquid Cooling (DLC) technology.

Key NVIDIA Vera Rubin Platform Features Include:

• NVIDIA NVLink™ 6: High-speed interconnects enabling unprecedented GPU-to-GPU and CPU-to-GPU communication for the training and inference of massive mixture-of-experts models.
• NVIDIA Vera CPU: NVIDIA-designed custom Arm cores delivering 2x performance over the previous generation, with spatial multithreading (88 cores/176 threads), 1.2 TB/s LPDDR5X memory bandwidth with 3x more capacity and 1.8 TB/s NVLink-C2C bandwidth to GPUs (2x previous).
• 3rd Generation Transformer Engine: Optimized acceleration for processing long-context workloads, narrow-precision computations critical to scale modern AI workloads.
• 3rd Generation Confidential Computing: Delivers rack-scale confidential computing with a unified, GPU-level trusted execution environment that keeps models, data, and prompts protected and isolated.
• 2nd Generation RAS Engine: Advanced reliability, availability, and serviceability features, including real-time health checks without downtime.

Additionally, the NVIDIA Vera Rubin platform benefits from newly announced NVIDIA Spectrum-X Ethernet Photonics networking, built on the Spectrum-6 Ethernet ASIC (102.4 Tb/s switching on TSMC 3nm with 200G SerDes co-packaged optics and fully shared buffers). This delivers 5x power efficiency, 10x reliability, and 5x application uptime compared to traditional pluggable optics. Available models include the liquid-cooled SN6800 (409.6 Tb/s CPO, 512x 800G ports), SN6810 (102.4 Tb/s CPO, 128x 800G ports), and SN6600 (pluggable, 128x 800G ports, air/liquid-cooled). Complementing this is Supermicro-based storage solutions using the Petascale all-flash storage server and JBOF system supporting the NVIDIA BlueField -4 DPU running a variety of data management solutions.

Supermicro's strategic investments in expanded manufacturing facilities and a comprehensive end-to-end liquid-cooling technology stack are purpose-built to streamline production and deployment of fully liquid-cooled NVIDIA Vera Rubin and Rubin platforms. Combined with the modular DCBBS architecture, these capabilities accelerate deployment and time-to-online by enabling rapid configuration, rigorous validation, and seamless scaling of high-density platforms—ensuring customers achieve first-to-market advantages.

About Super Micro Computer, Inc.

Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded and operating in San Jose, California, Supermicro is committed to delivering first to market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. We are a Total IT Solutions provider with server, AI, storage, IoT, switch systems, software, and support services. Supermicro's motherboard, power, and chassis design expertise further enables our development and production, enabling next generation innovation from cloud to edge for our global customers. Our products are designed and manufactured in-house (in the US, Taiwan, and the Netherlands), leveraging global operations for scale and efficiency and optimized to improve TCO and reduce environmental impact (Green Computing). The award-winning portfolio of Server Building Block Solutions® allows customers to optimize for their exact workload and application by selecting from a broad family of systems built from our flexible and reusable building blocks that support a comprehensive set of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air-conditioned, free air cooling or liquid cooling).

Supermicro, Server Building Block Solutions, and We Keep IT Green are trademarks and/or registered trademarks of Super Micro Computer, Inc.

All other brands, names, and trademarks are the property of their respective owners.

View original content to download multimedia:https://www.prnewswire.com/news-releases/supermicro-announces-support-for-upcoming-nvidia-vera-rubin-nvl72-hgx-rubin-nvl8-and-expanded-rack-scale-manufacturing-capacity-for-liquid-cooled-ai-solutions-302652755.html

SOURCE Super Micro Computer, Inc.

FAQ

What did Supermicro announce on Jan. 5, 2026 about NVIDIA Vera Rubin for SMCI?

Supermicro announced expanded US manufacturing and liquid-cooling solutions to enable deployment of NVIDIA Vera Rubin NVL72 and HGX Rubin NVL8 platforms.

What performance does the Supermicro NVL72 SuperCluster deliver for SMCI customers?

The NVL72 SuperCluster is described with 3.6 exaflops NVFP4, 1.4 PB/s HBM4 bandwidth, and 75 TB of fast memory.

What are the key specs of the Supermicro 2U HGX Rubin NVL8 system (SMCI)?

The NVL8 delivers 400 petaflops NVFP4, 176 TB/s HBM4 bandwidth, 28.8 TB/s NVLink, and ConnectX-9 networking.

How will Supermicro's manufacturing expansion affect SMCI deployment timelines?

Supermicro says expanded US-based manufacturing plus DCBBS and DLC accelerate configuration, validation, and rack-scale time-to-deployment.

Does Supermicro disclose the financial cost or capacity increase for its SMCI manufacturing expansion?

No—there are no cost, capacity-quantity, or financial guidance details disclosed in this announcement.