Our Products

The GemaTEG ecosystem. Deployed.

Active thermal management from the chip to the edge.
Modular Edge Data Center

GemaPOD

Sustainable AI compute, anywhere.
The Problem

Not every workload belongs in a hyperscale facility. Organizations that need AI compute closer to their operations face a hard tradeoff: either accept the latency, cost, and data sovereignty risks of a distant cloud, or build infrastructure that requires massive water systems, ideal climate conditions, and months of civil engineering.

The Solution

GemaPOD™ is a turnkey, modular data center powered by the full GemaTEG thermal management ecosystem. High-density AI compute with zero water consumption, ready to operate in any climate, in three to six months.

Zero water

Closed-loop architecture. No water consumption. No chiller dependency.

Any climate

Operates reliably in extreme heat, desert, arctic, or humid conditions.

Fast to deploy

Three to six months from order to operation. Pre-assembled and delivered to site.

Smart and connected

Remote monitoring, predictive maintenance, and federated networking.

Active Cold Plate - Chip Level

DaTEG® 1.5

The proven active thermal management system for current-generation AI chips and HPC servers.
The Problem

Data centers running today's high-density GPU workloads face two compounding problems. Conventional direct liquid cooling cannot prevent thermal throttling, leaving 60 to 70% of GPU performance on the table. And every infrastructure upgrade costs up to $1M per megawatt.

The Solution

DaTEG® 1.5 is GemaTEG's current production system, deployed and validated in mission-critical environments. It sits directly on the processor, controls temperature in real time, and operates with warm fluid above 40°C. No chiller is required. The right choice for organizations deploying today's GPU infrastructure at scale.

Up to 40% OpEx savings

Eliminating chillers and reducing energy consumption cuts operating costs from day one.

ROI under 12 months

No costly chiller infrastructure. Minimal upgrades required.

Sustainable

Zero water consumption. Operates in all climates.

Production-ready

Shipping now.

Active Cold Plate · Chip Level

DaTEG® 2.0

Active thermal management engineered for next-generation chiplet architectures.
The Problem

Next-generation chiplet architectures, with HBM stacks and compute dies running at different thermal loads, create multiple heat zones that a single cooling loop cannot address. Conventional direct liquid cooling was not designed for this. Neither were most of the systems being sold today as solutions.

The Solution

DaTEG® 2.0 is built for the chips arriving now and the next three to five generations that follow. While DaTEG® 1.5 addresses today's GPU infrastructure, 2.0 introduces independent temperature control across HBM and compute zones. This is a capability that chiplet architectures require, and conventional systems cannot provide.

DaTEG® 2.0 is here

From Development to Market-Ready. Active thermal management for the next generation of AI chips.

Up to 40% OpEx savings

Eliminating chillers and reducing energy consumption cuts operating costs from day one.

ROI under 12 months

No costly chiller infrastructure. Minimal upgrades as technology evolves.

Future-proof

Designed for the chips of today and tomorrow. One investment that doesn't need replacing every generation.

Sustainable

Zero water consumption. Operates in all climates.

Supervisor™

Software Options

Monitoring
Included
Preventive Maintenance
Available
Active Control
Available
Intelligent Passive Cold Plate

GemaTEG Smart Cold Plate

Thermal monitoring and protection for server infrastructure, without the complexity of a full active control system.
The Problem

Not every deployment requires the full active control architecture of DaTEG. But every deployment still needs better thermal performance than conventional cold plates can deliver. And every deployment needs to eliminate chiller dependency, without the cost and complexity of a full system overhaul.

The Solution

The GemaTEG Smart Cold Plate brings intelligent monitoring and predictive maintenance to standard server infrastructure. It operates with warm fluid above 40°C, integrates with Supervisor™, and gives operators real visibility into their thermal environment. It does not actively control temperature as DaTEG does, but it protects infrastructure, reduces energy waste, and serves as the natural entry point to the GemaTEG ecosystem.

Warm-fluid operation above 40°C

No chiller dependency. Lower infrastructure cost from day one.

Intelligent monitoring

Real-time visibility into thermal performance across the installation.

Predictive maintenance

Detect anomalies before they become failures.

Entry point into the GemaTEG ecosystem

Upgrade path to DaTEG® 1.5 or 2.0 as needs evolve.

Supervisor™

Software Options

Monitoring
Included
Preventive Maintenance
Available
How Our Products Integrate Together

One ecosystem. Every deployment.

Every GemaTEG product runs on the same foundation.

  • At the chip level, DaTEG® 1.5, DaTEG® 2.0, and the GemaTEG Smart Cold Plate each deliver thermal management suited to the deployment.
  • At the system level, Supervisor™ provides the monitoring, predictive maintenance, and active control layer that ties every product together.
  • GemaPOD™ brings the full ecosystem to edge locations, turnkey and ready to operate.
  • The GemaTEG TTV validates thermal performance at the design stage, before production begins.
Case Studies

Trusted by Sandia National Laboratories, Leonardo, and CERN.

In the Field

Deployed with organizations that cannot afford failure.

Mission-critical Performance With Less Energy
Challenge
  • Servers were overheating and throttling under intense compute loads.
  • Traditional cooling methods could not keep up with performance demands.
  • As a government lab, Sandia needed a long-term, energy- efficient solution that aligned with strict budget and sustainability goals.
Solution
  • GemaTEG installed DaTEGs on Intel Xeon 8480+ Platinum chips.
  • The system included Supervisor software for remote monitoring, on-site setup, and staff training.
  • The approach was collaborative, allowing Sandia to customize and test the solution on-site.
Expected Results
  • The deployment is expected to help Sandia maintain stable, high-performance compute under extreme thermal stress.
  • Server uptime should improve, with less heat-related wear and tear.
  • The partnership reflects Sandia’s pioneering spirit and strengthens collaboration with GemaTEG.
Commercial Potential

Ideal for national labs and research institutions facing similar high-intensity workloads. GemaTEG offers a testable, adaptive solution where failure is not an option.

A Strategic Leap Beyond Liquid Cooling
Challenge
  • Heat-related server failures were common, with traditional cooling unable to keep up.
  • Leonardo needed a cost-effective, high-performance solution to support growing compute demands.
  • Energy limits, sustainability targets, and tight public-sector budgets made this a long-standing, high-stakes problem.
Solution
  • Leonardo deployed GemaTEG’s Supervisor and DaTEGs on a NvidiaGPU platform to test against their existing liquid cooling.
  • The goal: higher performance, better efficiency, and longer hardware life.
  • Software integration added predictive maintenance and advanced energy controls.
Expected Results
  • The project is expected to achieve an average efficiency increase of 30%.
  • Anticipated benefits include longer hardware lifespan, reduced downtime, and lower emissions.
  • Success would position Leonardo as a forward-looking leader in sustainable high-performance computing.
Commercial Potential

Ideal for companies with systems hitting their limits, and under pressure to future-proof their infrastructure with sustainable solutions. It fits existing infrastructure and scales easily.

Ready to deploy?

Tell us about your infrastructure challenge. Our engineering team will identify the right product and path forward.