Navitas Semiconductor participated in NVIDIA’s Partner Ceremony on May 29, 2026, at the Taipei Nangang Exhibition Center as part of the NVIDIA AI Factory MGX ecosystem. The company is showcasing its 800 V-to-6 V DC-DC power delivery board (PDB) at the NVIDIA AI Factory MGX Ecosystem Showcase during COMPUTEX 2026 in Taipei from June 2 to June 5.
The PDB, powered by Navitas GaNFast technology, eliminates the traditional 48 V intermediate bus converter (IBC) stage in compute server trays. It features 16 GaNFast FETs rated at 650 V and 11 mOhms in the DFN8×8 dual-cooled package. The board targets 97.5% peak efficiency, operates at a 1 MHz switching frequency, and achieves a power density of 2100 W/in³. It is approximately 20% thinner than a mobile phone, enabling ultra-low profile integration close to the GPU board.
The solution supports emerging 800 VDC rack architectures for AI data centers.
“As AI workloads continue to scale and drive unprecedented demand for compute, power delivery has become one of the most critical challenges in enabling next-generation gigawatt AI factories,” said Chris Allexandre, President and CEO of Navitas. “Through our collaboration with NVIDIA within the MGX ecosystem, Navitas is delivering GaN and SiC power technologies that enable megawatt-scale AI server racks with higher power density, a smaller system footprint, and improved thermal performance.”
Navitas supplies GaNFast gallium nitride (GaN) solutions for high-frequency, high-efficiency DC-DC power conversion to support AI GPU power demands, enabling MHz-frequency operation, higher power density, and faster transient response. Its GeneSiC silicon carbide (SiC) portfolio supports power delivery from the grid to the AI compute rack, including solid-state transformers (SSTs) with 2300 V and 3300 V SiC power modules, and high-power three-phase power supply units (PSUs) using Generation 5 1200 V SiC MOSFETs.
The technologies are intended to support higher efficiency, power density, and system reliability in AI infrastructure. Navitas continues its collaboration with NVIDIA in the MGX ecosystem for open, modular AI infrastructure architectures.
