[Tallinn, 25.08.2025] – FORECR, a technology innovator in advanced embedded AI systems, is proud to announce the launch of its two new flagship products built around the powerful NVIDIA Jetson Thor Module: the DSBOARD-THRMAX, a compact carrier board for custom AI integration, and the DSBOX-THRMAX, an industrial-grade, enclosure-ready edge AI computer. These cutting-edge platforms are engineered to meet the growing demand for high-performance, real-time AI processing in robotics, automation, transportation, defense, energy applications and so on. 

At the heart of both systems lies the NVIDIA Jetson T5000, delivers an extraordinary 2070 TFLOPS of AI performance (FP4—Sparse), NVIDIA’s most advanced edge AI computing module, which delivers transformative performance over 7.5x higher AI compute of previous-generation Jetson platforms. Designed for the next generation of physical AI applications and humanoid robots, NVIDIA Jetson T5000 combines the latest NVIDIA accelerated computing architecture with 128GB of LPDDR5X memory and state-of-the-art interfaces to power massive AI workloads with low latency and energy efficiency — all in a compact module suitable for edge deployment. 

The DSBOARD-THRMAX is FORECR’s high-performance embedded carrier board tailored for system developers who demand flexibility and performance in compact dimensions (140x125mm). It offers extensive I/O including dual HDMI 2.1 and DP1.4a outputs, USB 3.2 Type-C, QSFP28 (4x 25 GbE), CAN, RS-232/422/485, and multiple digital I/Os. With dual M.2 slots supporting PCIe Gen5 storage, high-speed camera expansion, and wide-range power input (18–32V DC), this board is purpose-built for embedded AI applications in robotics, industrial automation, autonomous navigation, and AI-powered inspection systems. Wireless connectivity is enabled through extension sockets supporting WiFi, Bluetooth, LTE, and 5G modules.

Complementing the board-level solution, the DSBOX-THRMAX offers the same performance in a robust, thermally optimized enclosure designed. DSBOX-THRMAX — delivering supercomputer-class performance in an industrial PC form factor. Powered by the NVIDIA Jetson T5000, it provides up to 2070 TFLOPS (FP4 Sparse) of AI processing capability with 128 GB of high-bandwidth LPDDR5X memory. Engineered to run complex large language models alongside high-throughput video analytics, it enables advanced multi-modal AI workloads at the edge — seamlessly integrating real-time visual perception, contextual understanding, and decision-making into a single, deployable platform. 

Featuring ultra-fast connectivity via QSFP28 (4x 25 GbE), the DSBOX-THRMAX is built to move massive data streams effortlessly from multi-camera vision to real-time sensor fusion even in extreme -25°C to +85°C conditions. Optional 8x GMSL2 camera inputs and advanced high-speed I/O make it the ultimate platform for demanding multi-sensor AI at the edge making it ideal for advanced vision systems, autonomous machines, and real-time situational awareness platforms.  

“By integrating the exceptional computational capabilities of NVIDIA Jetson T5000 into compact and robust solutions, FORECR empowers developers and system integrators to accelerate AI at the edge without compromise,” said Mehmet Fatih KARAGOZ , Co-founder & CEO at FORECR.  

“These two products are a leap forward in making real-time, multi-sensor, AI-enabled intelligence scalable and deployable across industries.” 

For product inquiries, technical documentation, or partnership opportunities, visit www.forecr.io or contact sales@forecr.io. 

The DSBOARD-THRMAX and DSBOX-THRMAX will be available in September.