Steatite edge AI systems & accelerators offer real-time visual inference results without the need for high-bandwidth cloud connectivity.
Based on Nvidia CUDA accelerators including Jetson, GeForce, Tesla and Quadro, along with Intel Movidius VPUs.
Real-Time Inference – Running AI models on local hardware results in near-instant inference results.
Power Efficient –Specialist AI acceleration hardware and optimisation techniques helps reduce power consumption.
Frameworks – Regardless of the AI framework used, we can help to get your model running in a live environment.
Harsh Environment – Our Edge AI systems are designed to tolerate shock, vibration, hot, cold, water or dust.
Connectivity – AI Inference at the edge removes the bandwidth requirements associated with cloud-based AI.
Take a look at some of our AI systems and accelerators below, or contact one of the team to learn more.
Power efficient AI-at-the-edge inference systems, boards and modules based on Nvidia Jetson TX2, Nano & Xavier accelerators.
Power efficient AI-at-the-edge inference systems and add-on cards based on Intel Movidius accelerators.
High performance AI inference systems based on Nvidia GeForce and Quadro graphics cards and latest generation Intel CPUs.
• Optional Nvidia GPU / Intel VPU / FPGA.
• Full Length Dual Width GPU.
• Brushed Aluminium Panel.
• 8th / 9th Gen Intel Core CPU.
• 32GB DDR4 Memory Supported.
• Compact Embedded Chassis.
• Available For At Least 5 Years.
The Steatite AI-2000 is a high performance graphics/AI deep learning system designed for use in medical imaging, life science, surveillance and object recognition applications.
• Wide temperature operation.
• Two Mini PCIe slots.
• 12V and 5V DC outputs.
• RS232/UART/I2C/GPIO.
• 12-19VDC input.
• Two CAN Bus connectors.
Production-ready 12x12cm Jetson TX2 industrial-grade carrier board supporting -20°C to +70°C operation, CAN bus, Mini PCIe expansion, MIPI CSI-2, and 12V/5V output Simplifies transition from dev-kit to a system suitable . . .
• EN50155 GPU Computer.
• NVIDIA P1000 to P5000 Support.
• 8 x M12 Ethernet (inc. 4x PoE).
• 24V to 110VDC Input.
• Isolated LAN and Serial.
• Up to 7x Display Outputs.
Powered by an Intel® Core™ i7 CPU and integrated NVIDIA Quadro MXM module, ADLINK’s EN50155 certified AVA-5500 AIoT Platform comes supports up to 32GB DDR4 memory and either Windows or . . .
• Wide temperature operation.
• Standard & wide-temp options.
• 2 x CAN Bus connectors.
• Available until at least 2025.
Production-ready 87x50mm Jetson TX2 industrial-grade carrier board supporting up to -20°C to +70°C operation, CAN bus, RS232, and GPIO. Simplifies transition from dev-kit to a system suitable for mass production.
• Wide temperature operation.
• Available until at least 2025.
• 3 x Gigabit Ethernet.
• 2 x M.2 expansion slots.
• 120 pin MIPI CSI-II connector.
• 9 – 20VDC input.
• 2 x CAN Bus.
Compact production-ready Jetson Xavier AGX industrial-grade carrier board supporting -25°C to +80°C operation, CAN bus, and 3 x GbE. Simplifies transition from dev-kit to a system suitable for mass production.
Copyright Steatite Ltd / 2021 / All Rights Reserved
