LISBON - JULY 7, 2026 - FuriosaAI today announced the expanded availability of its RNGD AI inference accelerator across Europe. As an initial step, Furiosa is currently installing RNGD servers at Equinix’s Lisbon LS2 data center. In collaboration with Furiosa’s recently established flagship office in Lisbon, these on-site environments will enable European enterprises to evaluate the performance and ease-of-use of Furiosa’s architecture on cutting-edge models firsthand.
The deployment supports Furiosa’s growing European presence and comes at a critical juncture for the European tech ecosystem, where demand for efficient AI infrastructure continues to accelerate. Furiosa’s RNGD inference architecture – built on a 5nm Tensor Contraction Processor (TCP) architecture with 512 TFLOPS FP8 – delivers frontier model performance at a strict 180W thermal design profile per accelerator.
At the system level, up to eight RNGD accelerators are integrated into the NXT RNGD Server, a purpose-built inference engine designed to maximize compute density for production AI workloads. Operating as a 3kW-class inference system, the server enables significantly higher inference capacity per rack while maintaining a strong performance-per-watt profile for agentic AI applications.
These capabilities are optimized for deployment environments where power availability and rack density are critical constraints, enabling scalable AI infrastructure within modern data centers.
“We are pleased to be establishing an important new distribution channel in Europe with Equinix,” said Furiosa Co-Founder and CEO June Paik. “By pairing Equinix’s infrastructure footprint designed for efficiency and sustainability with our high-performance, energy-efficient RNGD architecture, we unlock the ability for enterprises to run inference sustainably and reliably.”
The announcement coincides with the RAISE Summit in Paris, where Furiosa is showcasing its latest production-ready hardware and software. Furiosa recently announced a partnership with Broadcom to develop its third-generation inference accelerator, designed to deliver breakthrough performance per watt when running the largest frontier models, with a trillion or more parameters, at hyperscale inference infrastructure.
About FuriosaAI
FuriosaAI builds high-performance, high-efficiency AI compute for the Inference Era. Founded in 2017 by veteran semiconductor and AI algorithm engineers, Furiosa operates globally with offices in Korea and Silicon Valley, along with a compiler-focused R&D lab in Lisbon. The company has shipped two generations of AI chips based on its proprietary Tensor Contraction Processor (TCP) architecture. Its flagship product, RNGD, runs advanced large language models and agentic AI and is now in mass production. RNGD deploys directly into standard, air-cooled data centers—no liquid cooling or facility retrofits required—delivering industry-leading tokens-per-watt efficiency, backed by a mature software stack that makes deployment straightforward. The company has raised more than $250M through Series C Bridge and works with leading global partners, including TSMC, SK hynix, and Broadcom.
Written by
