Navitas Collaborates with NVIDIA on 800 V-to-12 V Power Delivery Board for Next-Generation AI Infrastructure
Key Highlights
- ➤24 kW 800 V-to-12 V board developed with NVIDIA for AI infrastructure
- ➤97% target efficiency and over 2,000 W/in³ power density at full load
- ➤Single-stage conversion eliminates the existing 50 V-to-12 V IBC stage
- ➤Navitas plans to showcase the board at OCP Global Summit 2026
Expert Statements
Chris Allexandre, President and CEO of Navitas
“The next era of AI will be defined not only by how much compute we can create but by our ability to deliver the power needed to unleash its full potential.”
Chris Allexandre, President and CEO of Navitas
“Our collaboration with NVIDIA is breaking the AI infrastructure power wall by reimagining power delivery from 800 VDC to the GPU.”
Chris Allexandre, President and CEO of Navitas
“This next-generation 24 kW solution demonstrates how GaNFast™ technology can eliminate power-conversion stages, increase efficiency and power density, and bring power closer to the GPU.”
TORRANCE, Calif., Oct. 12, 2026 (GLOBE NEWSWIRE) -- Navitas Semiconductor (Nasdaq: NVTS), a leader in next-generation power semiconductors and power delivery solutions, pioneering GaN, high-voltage and ultra-high-voltage SiC, and IVR technologies, today announced its latest 24 kW, 800 V-to-12 V DC-DC power delivery board (PDB), powered by GaNFast™ technology and developed in collaboration with NVIDIA, to support the NVIDIA MGX ecosystem and advance 800 VDC power architectures for AI data centers. The new PDB is planned to be featured on NVIDIA’s AI Factory MGX Wall partner display area at OCP Global Summit 2026.
This latest 24 kW, 800 V-to-12 V PDB extends Navitas’ portfolio of 800 VDC AI data-center platforms, building on the previously announced 20 kW, 800 V-to-6 V PDB developed in collaboration with NVIDIA. These solutions advance the core strategic focus of the Navitas 2.0 transformation to accelerate the replacement of legacy silicon with next-generation GaN and SiC high-power technologies across AI infrastructure, from Grid-to-xPU.
Get started
Create a free account to read the full story.