7STARLAKE Launches F50 Airborne Liquid-Cooled AI Super Server
July 13, 2026
News
7STARLAKE introduced its F50 Airborne Liquid-Cooled AI Super Server engineered to meet ARINC 429 avionics standards that support mission-critical airborne functions including navigation, flight control, and engine monitoring. The solution integrates an optimized liquid-cooling design to ensure consistent operation in harsh airborne operating environments. It is built on 7STARLAKE’s Open Modular and Scalable Architecture.
Powered by the Xeon Granite Rapids-D 6726P-B SoC, it features 42 cores with base and turbo frequencies of 2.3 GHz and up to 3.5 GHz ideal for database management, virtualization, and cloud computing. It supports VMware v8 and later for long-term IoT and embedded deployments.
Utilizing the NVIDIA Blackwell RTX PRO 6000 Tensor Core GPU (24064 CUDA), the F50 delivers up to 120 TFLOPS of FP32 performance, peak FP4 AI performance of up to 4 PFLOPS, and 355 TFLOPS of ray tracing capability. With a PCIe Gen 5 x16 high-speed interface, it permits real-time inference on trained neural network models for high throughput and low latency in harsh environments.
The platform supports up to 512 GB of RDIMM ECC DDR5 memory operating at 6400 MHz that provides high bandwidth and data integrity for AI-intensive and real-time processing tasks. Two U.2 NVMe slots enable high-speed storage access and future expansion with optional 8 ADC / 8 DAC RFSoC configurations available to support advanced airborne signal acquisition, sensor fusion, and radar or EW processing applications.
Engineered to meet MIL-STD-810 and MIL-STD-461 standards for shock, vibration, electromagnetic compatibility, and extreme temperature operation, it supports ARINC 429 and MIL-STD-1553 avionics and military communication interfaces. For security, the F50 supports the Trusted Platform Module (TPM) 2.0.
For more information, visit 7starlake.com/products/defense/air-borne/f50.
Chad Cox is the Production Editor at Embedded Computing Design. His responsibilities are centered around content creation, writing and editing, and article research and development. Chad covers industry news and events and is known to interact with various industrial leaders via on-premise visits and online interviews. He is responsible for the digital footprint and dissemination of news via social media posts, advertising creation and the production of newsletters including the Embedded Computing Design’s Daily.
He is well versed in many facets of industrial computing including Edge AI, IoT, Processing, Security, Open Source, and more.
Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature and holds a master’s in education.
