The tech giant's new rack-mounted cooling solution handles chips drawing over 1,000 watts and will be open-sourced for industry-wide adoption
Google just dropped its answer to one of the biggest bottlenecks in the AI infrastructure race: keeping the hardware from melting. The company’s new Brazos liquid cooling system is a rack-mounted, closed-loop solution designed specifically for the kind of power-hungry chips that are becoming standard in AI and high-performance computing workloads.
The system can handle thermal loads up to approximately 60kW per rack. For context, that’s roughly enough to cool chips with a thermal design power exceeding 1,000W, which is the territory occupied by the latest generation of AI accelerators.
What Brazos actually does #
Brazos is a liquid-to-air system that circulates either deionized water or a coolant mixture containing 25% propylene glycol through the rack. The liquid absorbs heat directly from the chips, then transfers it to air, which gets exhausted from the system.
Because Brazos operates as a closed-loop system at the rack level, data center operators can deploy it in existing air-cooled facilities without requiring facility-wide retrofits.
Google also built in several safety features that address the obvious concern with running liquid near millions of dollars worth of computing hardware. The system includes leak detection, pressure relief valves, and hot-swappable pumps and fans. That last detail matters because it means operators can replace failing components without shutting down the rack.
This isn’t Google’s first foray into liquid cooling. The company has been running liquid-cooled systems since 2018, when it introduced the Tensor Processing Unit v3. Since then, Google has deployed liquid cooling across more than 2,000 TPU pods, achieving approximately 99.999% uptime. In practical terms, that’s about five minutes of downtime per year.
The open-source play #
Perhaps the most significant aspect of the Brazos announcement is what comes next. Google plans to open-source the specifications and designs for the system in the coming months.
The timing also aligns with Google’s massive capital expenditure plans. The company has committed to a $40 billion investment in data center infrastructure in Texas alone, part of a broader buildout to support its AI ambitions.
What this means for investors in the digital asset space #
Google didn’t mention crypto, blockchain, or digital assets anywhere in the Brazos announcement. But the same thermal challenges that plague AI data centers also affect large-scale cryptocurrency mining operations and blockchain infrastructure, where cooling costs represent a significant portion of operational expenses.
The open-sourcing decision is particularly relevant here. If Brazos designs become freely available, smaller operators who can’t afford proprietary cooling solutions from companies like CoolIT or Vertiv could adopt Google’s approach instead.
Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our