Best practices for deploying liquid-cooled servers in AI data centers
To learn more about how to plan, deploy, and scale liquid cooling for AI-ready data centers, explore our liquid cooling resources
NVIDIA's Rubin generation AI infrastructure is the first to feature a fully liquid-cooled architecture, with every chip and networking component cooled through a closed-loop liquid system that eliminates the need for fans. Hot tubs sit at about 38 to 40 d...
HOME / AI Fully Liquid-Cooled Server - DKN Access Networks & Consulting
AI Fully Liquid-Cooled Server - DKN Access Networks & Consulting [PDF]
To learn more about how to plan, deploy, and scale liquid cooling for AI-ready data centers, explore our liquid cooling resources
9th-generation V-NAND, 4nm controller and liquid-cooling optimization support demanding AI workloads Samsung Electronics a global leader in advanced memory technology,
NVIDIA''s latest data center servers use 113°F liquid cooling, which cuts energy use, water consumption and reliance on traditional chillers.
The company announced on Monday that its newest AI servers will entirely use liquid cooling, a method that eliminates the need for air-cooling fans that rely on water.
Solidigm, a pioneer in enterprise data storage, unveiled at the GTC AI Conference today one of the world''s first liquid-cooled enterprise solid state drives (eSSDs)—helping remove the fans
For its Rubin-generation AI infrastructure, it will use a closed-loop liquid cooling system to cool all major components, including chips and network equipment, without the need for fans.
Discover ASUS AI POD powered by NVIDIA Vera Rubin NVL72: 100% liquid-cooled rack-scale infrastructure with 72 Rubin GPUs, ultra-efficient
Nvidia has announced a liquid cooled server rack featuring 72 of its newly shared Blackwell GPUs. The GB200 NVL72 system also includes 36 Grace CPUs and nine NVLink switch
Discover liquid cooling best practices for AI data centers, including design, deployment, maintenance, and sustainability benefits.
The NVIDIA GB300 NVL72 features a fully liquid-cooled, rack-scale architecture that integrates 72 NVIDIA Blackwell Ultra GPUs and 36 Arm®-based NVIDIA Grace™ CPUs into a single platform. The
As a provider of NVIDIA GB300 NVL72 and NVIDIA HGX B300 systems, the flagship ASUS offering is the ASUS AI POD built on NVIDIA Vera Rubin platform – a liquid-cooled, rack-scale
MSI showcased liquid-cooled ORv3 racks up to 100kW, NVIDIA MGX servers, the XpertStation WS300 DGX Station, and DC-MHS platforms at
The Dell PowerEdge XE8812 is a fanless, direct liquid-cooled server designed for dense AI and HPC deployments. Unlike conventional servers that rely heavily on air cooling, the system
DIGGERS develops fully integrated, liquid-cooled data center systems. Hermetically sealed, energy-efficient, PUE < 1.05. Direct-to-Chip cooling for AI workloads.
Data center operators are evaluating liquid cooling options, as processing-intensive computing applications grow. The market for liquid cooling is slated to reach $3 billion USD by 2026, as
Supermicro is introducing its 100% direct liquid-cooled rack solution powered by the NVIDIA Vera CPU — a fully integrated system designed to handle the emerging requirements of agentic AI and the
From hundreds of billions of dollars in capital expenditure by North American cloud vendors to the mass launch of domestic intelligent computing centers; from AI server production lines running
Warm liquid AI cooling is redefining how AI infrastructure manages heat by using high-temperature liquid instead of traditional air cooling. NVIDIA''s latest fully liquid-cooled AI servers
An increasing number of servers require liquid cooling systems to support AI workloads. Depending on the scale of liquid-cooled server deployments, a data center can be cooled through exsiting or
The fully liquid-cooled design significantly reduces cooling energy consumption, addressing one of the largest contributors to data centre power usage. Cooling has historically accounted for up
The solution combines a fully integrated, liquid-cooled system with commissioning, deployment, and ongoing maintenance services, along with unified warranty coverage across the
Super Micro Computer (NasdaqGS:SMCI) has been named a global system builder and launch partner for NVIDIA''s new Vera Rubin NVL4 AI platform. The company unveiled next
Liquid cooling is essential for AI-driven data centres, efficiently managing the extreme heat generated by high-density AI server racks. It offers
In data centers with liquid cooling, typically only 10% of racks or fewer are using it. But as AI workloads are deployed at a runaway pace, liquid cooling is becoming
Among these, AI training server liquid cooling penetration is most prominent, surging from 15% in 2024 to 74% in 2026, potentially reaching 80%
NVIDIA''s newest AI servers can run their cooling liquid even hotter — up to 45 degrees Celsius, or 113 degrees Fahrenheit. That higher temperature limit is precisely what makes them more energy efficient.
The closed-loop system also enables waste heat recovery for nearby commercial or residential buildings where conditions permit. To achieve a fully liquid-cooled server, NVIDIA
JetCool introduces a liquid-cooled Dell PowerEdge XE7745 server, enabling high-density AI deployments with improved cooling, efficiency, and scalability.