EdgeCortix is redefining AI by enabling powerful, efficient intelligence to run reliably inside embedded and industrial systems, from a single low-power accelerator to scalable Physical AI platforms.See SAKURA-II Live
Visit Stall A3 for live demonstrations of our latest models, including LLMs, VLMs, and ViTs, running on the SAKURA-II Edge AI Platform. SAKURA-II delivers up to 60 TOPS (INT8) in a typical 8W power envelope, with low-latency Batch=1 inference, up to 32 GB of DRAM, and best-in-class memory bandwidth. It is available today in compact M.2 and PCIe form factors and supported by the MERA software stack and the new MERA Studio desktop application.
Introducing RAIDEN-X4: The Physical AI compute platform that adapts as models change and scales as systems grow
Physical AI is more than one fast model. It is a continuous loop of sensing, reasoning, planning, and acting. RAIDEN-X4 is a scalable, energy-efficient chiplet platform designed to run that entire workload. It combines our new DNA-X architecture with on-package 64-bit RISC-V cores and scales to 3,360 FP4 TFLOPS and 256 GB of LPDDR5X memory. Talk to our team about how RAIDEN can power robotics, Industry 4.0, smart infrastructure, and edge data centers. You can also ask about our Early Access Program ahead of customer sampling in early 2027.
One Architecture, One Software Stack
Models you build on SAKURA-II today move forward with you. MERA supports Hugging Face, ONNX, ExecuTorch, and TensorFlow Lite on x86, Arm, and RISC-V hosts, and extends to RAIDEN. It’s new silicon with a proven toolchain.
Built for India’s Embedded Ecosystem
With our India Research Center in Hyderabad, EdgeCortix is invested in India’s fast-growing semiconductor and embedded systems community. Stop by Stall A3 to meet the team.
