Connect with us

Hi, what are you looking for?

AI Technology

Toradex Launches OSM and Lino COMs for Edge AI with NXP i.MX 91 and 93 Chips

Toradex unveils OSM and Lino COMs, powered by NXP i.MX 91 and 93 chips, delivering cutting-edge edge AI performance with up to 0.5 TOPS for IoT and industrial automation.

Swiss embedded computing specialist Toradex has announced the launch of two new computer-on-module (COM) families, named OSM and Lino, which are targeted at the industrial automation and Internet of Things (IoT) sectors. This release underscores the company’s commitment to providing compact and reliable solutions for industrial edge AI computing.

“Both families deliver new compact, reliable, industrial edge AI compute platforms,” said Samuel Imgrueth, CEO of Toradex. He noted that while the OSM series integrates a solderable standard form factor, the Lino family offers connector-based ease of use for rapid integration and serviceability. This development aims to empower customers to design next-generation, intelligent, space-constrained devices with confidence, scalability, and long-term support.

The OSM family adheres to the Open Standard Module specification, Size-S variant, allowing for a compact design that measures just 30×30mm (approximately 1.18×1.18″). It features a ball grid array (BGA) footprint for direct soldering onto a host carrier board. In contrast, the Lino family maintains the same dimensions but employs dual 100-pin board-to-board connectors underneath, enabling easy removal from its carrier board for straightforward replacement.

Both the OSM and Lino formats share the same core hardware, starting with the base-level model, either the Lino or OSM iMX91, which is built around the NXP Semiconductors i.MX 91 system-on-chip. This model features a single Arm Cortex-A55 core capable of running at speeds up to 1.4GHz, along with up to 2GB of LPDDR4 RAM and 16GB of eMMC flash that can be expanded to 256GB. For users requiring enhanced performance, the Lino or OSM iMX93 variant is available, equipped with the NXP i.MX 93, which includes two Cortex-A55 cores operating at up to 1.7GHz, a companion real-time Cortex-M33 core running at up to 250MHz, and an optional neural coprocessor that offers 0.5 tera-operations per second (TOPS) for on-device machine learning and AI tasks.

To further facilitate integration, Toradex has introduced the Verdin-Lino adapter. This interstitial board accepts a Lino COM and adapts it to the SODIMM form factor of the company’s previous Verdin COMs, allowing Lino to function as a drop-in upgrade. On the software front, Toradex provides a Yocto reference Linux image and offers support for its proprietary Torizon platform.

With the launch of the OSM and Lino families, Toradex is poised to enhance the capabilities of developers and engineers working on IoT and industrial automation projects. The introduction of these advanced computing solutions highlights the growing demand for efficient and flexible computing platforms in an increasingly interconnected world, signaling the company’s strategic focus on meeting the evolving needs of the market.

See also
Staff
Written By

The AiPressa Staff team brings you comprehensive coverage of the artificial intelligence industry, including breaking news, research developments, business trends, and policy updates. Our mission is to keep you informed about the rapidly evolving world of AI technology.

You May Also Like

AI Regulation

QUALCOMM amends bylaws to enhance shareholder rights and governance, allowing 25% owners to call special meetings as it pivots to AI chips and IoT.

© 2025 AIPressa · Part of Buzzora Media · All rights reserved. This website provides general news and educational content for informational purposes only. While we strive for accuracy, we do not guarantee the completeness or reliability of the information presented. The content should not be considered professional advice of any kind. Readers are encouraged to verify facts and consult appropriate experts when needed. We are not responsible for any loss or inconvenience resulting from the use of information on this site. Some images used on this website are generated with artificial intelligence and are illustrative in nature. They may not accurately represent the products, people, or events described in the articles.