OmniTherm delivers single-slot, waterless two-phase cooling to increase PCIe GPU density and reduce operational burden at scale.
Foster City, CA — 16 March 2026 — ZutaCore, a leader in waterless, direct-to-chip, two-phase liquid cooling, today announced that its OmniTherm cold plate enables waterless two-phase cooling for manufacturers building servers with the NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs in a single-slot PCIe form factor — supporting full-power operation in standard enterprise and AI cloud server environments.
As AI inference expands rapidly across enterprise and cloud environments, PCIe GPU servers have become a preferred platform because they are easy to deploy, scale, and integrate into existing infrastructure. As GPU power rises, however, air cooling can become a limiting system factor — restricting density, driving up fan power, which in turn increases the risk of thermal throttling during sustained workloads.
OmniTherm removes these barriers by enabling a transition to two-phase liquid cooling without introducing water inside the server. The single-slot design allows operators to increase accelerator density in standard server architectures while capturing heat into a liquid loop, reducing reliance on extreme fan speeds that can create excessive noise, waste power, and cause challenging operating conditions in the data centre.
Enterprise and cloud operators want the flexibility of PCIe GPUs, but they also need density and sustained performance as power levels rise. OmniTherm delivers waterless two-phase cooling in a single-slot form factor, helping data centres increase accelerator density while maintaining stable thermals for 24/7 AI workloads.
Built for Always-On AI Operations
Production AI workloads — especially inference — are rarely steady. They fluctuate constantly, creating thermal swings that can impact performance and reliability. OmniTherm's two-phase cooling adapts to these dynamic thermal loads without external controls. The refrigerant absorbs and releases heat through phase change, maintaining consistent GPU junction temperatures regardless of workload variation.
This passive thermal regulation supports sustained GPU boost clocks without throttling, even under mixed or bursty inference patterns — a critical requirement for always-on AI services in enterprise and cloud environments.
Key Benefits
Single-slot PCIe form factor: Direct replacement for air-cooled GPU cards, no chassis modifications required
Waterless two-phase cooling: No water inside the server, eliminating leak risk and simplifying compliance
Increased GPU density: Enables higher accelerator counts per server by removing airflow constraints
Passive thermal regulation: Phase-change cooling adapts to dynamic AI workloads without external controls
Reduced fan power and noise: Lower reliance on high-speed fans cuts energy use and improves data centre conditions
The announcement comes ahead of NVIDIA GTC 2026, where ZutaCore will demonstrate OmniTherm cooling the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU.
