Q.ANT and Ionos launch second-generation photonic AI pilot

By Elena Vasquez

Ionos will host Q.ANT’s second-generation Native Processing Unit (NPU) on a bare-metal server in a German data center and give approved applicants access through its website. The pilot lets users run and evaluate their own workloads with their own data and software.

What does the pilot let developers test?

The program lets companies, researchers and developers explore algorithms and AI architectures built around the NPU’s ability to compute complex nonlinear functions. Q.ANT and Ionos say it can support “leaner AI models” that use those functions directly and run faster.

They also expect models to deliver “comparable or better results” with fewer parameters, fewer operations and fewer resources. Those remain partner claims: the announcement includes no pilot workloads, accuracy measurements, throughput figures or energy results.

Ionos has not identified the German data center hosting the server. Its website lists a facility in Berlin and leased space from Equinix in Frankfurt within its German footprint, while the company operates 32 data centers worldwide.

Dr Michael Förtsch, Q.ANT’s founder and CEO, said:

“A new computing architecture only becomes commercially relevant when customers can test it against the workloads that matter to them. When we launched our SDK, developers could begin building applications for photonic computing. Now, with Ionos, they can take their work and run those applications on the real processor.

This matters because the conversations around AI are shifting from what the models can do to what it costs to run them. Photonic computing can make the next generation of AI models leaner: complex functions that inflate digital models can be computed with fewer data and parameters with light, resulting in less energy requirements for the same workloads.”

What changes for Ionos?

Ionos CEO Achim Weiss said:

“Promising computing technologies from Europe need sovereign European infrastructure to make the leap into business use. In the pilot program, Q.ANT’s photonic processor runs in an Ionos data center under German jurisdiction. Users can explore processing with light on their own workloads.

The results will show which applications benefit most and will feed directly into our future development work.”

In May, Ionos became the first commercial cloud data center customer for Q.ANT’s Native Processing Server (NPS). Ionos also belongs to Virt8ra, a sovereign Edge cloud testbed in Europe that launched in January 2025.

How does the chip work?

Q.ANT, headquartered in Stuttgart, Germany, was founded in 2018 as a spin-off from industrial firm TRUMPF. It develops photonic chips built on thin-film lithium niobate (TFLN).

Those chips execute mathematical operations directly in the optical domain using photonic integrated circuits. Q.ANT says this approach eliminates on-chip heat generation and cooling requirements. The pilot aims to identify where photonic processing offers the greatest advantage and provide the validation needed for broader commercial deployment.

Which performance claims need testing?

Q.ANT says the Native Processing Server integrates “seamlessly” into data centers as a plug-in co-processor. It claims energy efficiency of up to 30 times and performance gains of 50 times, with potential to increase data-center capacity 100 times without complex active cooling systems.

The announcement provides no baseline, test method or independently measured result for those ratios. They remain vendor claims, not pilot findings. The program will test whether fewer parameters, operations and resources can produce comparable or better AI results on customers’ own workloads.

Q.ANT raised €62 million ($72 million) in a Series A funding round in July 2025, co-led by Cherry Ventures, UVC Partners and imec.xpand. The announcement gives no pilot end date, admission schedule or commercial terms. The next milestone is measured performance from approved users.

Wider deployment therefore depends on those workload results, which the partners say will identify the applications that benefit most and feed directly into Ionos’s future development work.