Modalix™ in Production, Now Shipping SoM Pin-Compatible with leading GPU SoM, Dev Kits, and LLiMa for Seamless LLM-to-Modalix Integration
SiMa.ai, a leader in Physical AI innovation, has announced three major product launches designed to accelerate the global adoption of Physical AI technologies. These include the production release of its next-generation Physical AI silicon, MLSoC Modalix™; the immediate availability of a pin-compatible System-on-Module (SoM) and development kit; and the introduction of LLiMa™, a software framework for deploying high-performance LLM and GenAI models on Modalix.
Modalix™: Purpose-Built for Physical AI at the Edge
The second-generation Machine Learning System on a Chip (MLSoC™), Modalix™, is engineered to set new standards for the Physical AI sector. Designed for under 10-watt operation, it delivers exceptional performance and accuracy while supporting LLMs, transformers, CNNs, and GenAI workloads. Its flexible Arm-based architecture, paired with a native GenAI software stack, enables real-time perception, decision-making, and natural language interaction. Modalix supports a comprehensive set of interfaces including camera, Ethernet, and PCIe making it ideal for scaling Physical AI across robotics, automotive, industrial automation, aerospace and defense, smart vision, retail, and medical applications.
“SiMa.ai’s Modalix showcases the scale of innovation that’s possible building on Arm’s flexible, high-performance, power-efficient compute platform,” said Ami Badani, Chief Marketing Officer, Arm. “By bringing AI and LLM capabilities to Physical AI applications at the edge, SiMa.ai is enabling smarter, faster, and more sustainable systems across industries.”
Developed using Synopsys’ AI-powered EDA suite, broad IP portfolio, and advanced design solutions, Modalix achieved bug-free A0 silicon on its first tapeout, ensuring rapid and confident production.
Also Read: Microsoft Integrates OpenAI’s GPT-5 Across Products to Deliver Advanced AI Reasoning Capabilities
“The development of Physical AI applications requires validated, purpose-built silicon and software that is only possible using the most advanced design solutions,” said Ravi Subramanian, Chief Product Management Officer, Synopsys. “Achieving a successful first tapeout of MLSoC Modalix illustrates the mission-critical role of Synopsys AI-powered design and IP to achieve complex SoC requirements. Together, Synopsys and SiMa.ai are enabling customers to bring their bleeding-edge AI innovations to market faster and with confidence.”
Manufactured with TSMC’s advanced N6 process, Modalix meets the demanding power, thermal, and reliability requirements of embedded deployments.
“TSMC is proud to deepen our collaboration with industry innovators like SiMa.ai to deliver advanced SoCs enabled by TSMC’s leading-edge process technology, meeting the rapidly growing demand for Physical AI,” said Sajiv Dalal, President of TSMC North America. “This collaboration underscores our commitment to driving energy-efficient chip innovations that are redefining the future of AI.”
“The era of Physical AI is here! With Modalix™ now in production, we’re accelerating its global adoption,” said Krishna Rangasayee, founder and CEO of SiMa.ai. “Demand for our Modalix SoM is strong, and we’re excited to launch it worldwide. We’re also introducing LLiMa to simplify LLM deployment on Modalix, making it easier than ever to bring GenAI to Physical AI systems.”
SoM and Devkit: Fast-Tracking Physical AI Deployment
The new Modalix SoM is pin- and form-factor compatible with leading GPU-based modules, enabling a seamless drop-in replacement for rapid system integration. Compact and power-efficient, it integrates MIPI, memory, and essential I/O to meet the needs of scalable Physical AI deployment.
“This Enclustra-SiMa.ai SoM is more than just a module – it’s a powerful, ready-to-deploy physical AI platform,” said Philipp Baechtold, CEO of Enclustra. “Together with SiMa.ai, we’ve created a plug-and-play development kit that enables fast, efficient deployment of advanced AI applications across industries like robotics, smart vision, and healthcare.”
Bundled with SiMa.ai’s Palette™ software, full ML framework support, integrated cooling, MIPI camera compatibility, and SSD storage, the SoM devkit empowers developers to move from prototype to production faster than ever before.
LLiMa™: On-Device LLM Deployment with Zero Cloud Dependency
LLiMa™ is a unified on-device framework for running LLMs, LMMs, and VLMs on Modalix™ without reliance on the cloud. It offers seamless import of open-source or custom LLMs, a curated model library, and automated quantization and compilation to produce Modalix-ready binaries. With full on-device support for agent-to-agent systems, Model Context Protocol (MCP), and Retrieval-Augmented Generation (RAG), LLiMa™ enables cutting-edge Physical AI applications to operate with unmatched speed, security, and efficiency.