Sparxity, a Dresden, Germany-based developer of specialized AI computing hardware, has closed a Series A funding round led by ICM HPQC Fund, bringing its cumulative funding to $90 million. The amount raised in the Series A round was not disclosed.
The round included participation from Lockheed Martin Ventures, GlobalFoundries, GS Futures, Cloudberry Ventures, TGFS and the EIC Fund. Angel investors Richard Socher and Nancy Xu also participated, alongside continued support from Atlantic and Silicon Catalyst.
Founded in 2021 and formerly known as SpiNNcloud, Sparxity develops specialized processors and computing systems for AI and high-performance computing applications. The company is led by co-founder and CEO Hector Gonzalez. Its other co-founders include CTO Matthias Lohrmann and Christian Georg Mayr.
Sparxity builds computing infrastructure designed around dynamic sparsity, an approach that activates only the computational resources required for a particular task. Its technology combines custom silicon, computing hardware and software to reduce unnecessary processing and data movement in AI workloads.
The company plans to use the funding to accelerate development of specialized chips for fine-grained dynamic sparsity in AI inference. Its next-generation hardware targets faster inference and lower energy consumption for ultra-sparse AI models.
According to the company, it has completed three chip tapeouts, produced more than 70,000 chips and deployed 12 computing racks. Sparxity reports serving more than 30 customers worldwide, including major supercomputing facilities.
In October 2026, Sparxity announced a multimillion-dollar deployment of its computing systems at Germany’s Jülich Supercomputing Centre. The company also announced a planned collaboration with Deutsche Telekom’s T-Systems to integrate sparse-native computing technology into data centre infrastructure.

