Steatite edge AI systems 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 and Arria FPGAs.

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 – Edge AI inference is ideal for use when shock, vibration, temperature, water or dust can be a problem.
Connectivity – Inference at the edge reduces bandwidth requirements, but we can offer 4G/5G, WiFi & LAN connectivity.

Take a look at some of our AI systems and accelerators below, or contact one of the team to learn more.

  • Inference / Deep Learning Accelerator Cards

    Low-latency FPGA & Movidius based Inference acceleration cards for AI edge computing.

  • ITG-100AI

    Key Features

    • 2 x Intel Myriad X VPU For AI.
    • Intel Atom x5-E3930 CPU
    • 2 x Gigabit Ethernet Ports
    • 2 x RS-232/422/485 Serial Ports
    • M.2 A-key Slot Expansion
    • -20°C to 50°C Operating Temp

    Quick Overview

    The ITG-100AI can run AI faster, and is well suited for low power consumption applications such as surveillance, retail and transportation. With the advantage of power efficiency and high performance . . .

  • Key Features

    • 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.

    Quick Overview

    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.

  • Axiomtek AIE500-901-FL

    Key Features

    • GPU Accelerated AI Computing .
    • 256 CUDA Cores.
    • -30 to +60°C Operating Temp.
    • USB 3.1/COM/CAN Support.
    • M.2/PCIe/SATA/MicroSD.
    • JetPack Supported.

    Quick Overview

    The Axiomtek AIE500-901-FL is a compact  and fanless edge AI system with NVIDIA® JETSON TX2 series SoM, 8GB LPDDR4 memory on board and support for Linux based operating systems.

  • ADLINK AVA-5500

    Key Features

    • EN50155 Certified for Rail.
    • 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.

    Quick Overview

    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 . . .

  • Key Features

    • 8th / 9th Gen Intel® Core™ CPU
    • 4 Channel PoE (IEEE802.3at)
    • Dual Swappable 2.5″ HDD Bays
    • MXM 3.1 Type A GPU Support
    • Triple Independant Display
    • Intelligent Remote Monitoring

    Quick Overview

    The Axiomtek eBOX671-521-FL is a GPU computing embedded system that comes with 4 channel PoE and MXM 3.1 Type A slot for applications in machine vision, edge computing, traffic vision, . . .

  • Key Features

    • ROS2-enabled Robotic Controller
    • NVIDIA® Xavier™ AGX
    • Field Control I/O Interface
    • Optional Expansion Function
    • 9V – 36V DC Input
    • -20°C to 70°C Operating Temp

    Quick Overview

    The ADLINK M300-Xavier-ROS2 is a fanless robotic controller taking advantage of server-class performance of NVIDIA® Jetson AGX Xavier™ to enable autonomous navigation in automated mobile robots (AMR).

  • Key Features

    • Compact Fanless System
    • Deep Learning Acceleration
    • NVIDIA® Jetson™ TX2
    • Up to 8GB Memory Supported
    • 16GB eMMC Storage
    • -20°C to 70°C Operating Temp

    Quick Overview

    To deliver Artificial Intelligence (AI) at the edge, ADLINK’s DLAP-201-JT2 Edge AI Platform integrates NVIDIA® Jetson™ TX2 to accelerate deep learning workloads for object detection, recognition and classification.

  • Key Features

    • NVIDIA® Jetson™ Nano
    • 4GB Memory & 16GB eMMC
    • 8 x Gigabit Ethernet/PoE
    • HDMI / 8 Bit DIO / COM / USB
    • 2.5″ SATA Storage
    • 12V DC Power Input

    Quick Overview

    The ADLINK M100-Nano-AINVR is a compact multi-channel AI-enabled NVR powered by NVIDIA® Jetson Nano™, meeting size, weight and power (SWaP) requirements for identity detection and autonomous tracking in public transport . . .

  • AI-1000-MV

    Key Features

    • 8/16 x Intel Myriad X VPUs
    • 8th Gen Intel Core Series CPU
    • Up to 32GB DDR4 RAM
    • Up to 10x Gigabit Ethernet
    • 9 to 48V DC Power Input
    • Intel OpenVINO Support

    Quick Overview

    The Steatite AI-1000-MV is a high performance industrial computer for visual AI inference applications. Utilising 8 or 16 Intel Movidius Myriad X MA2485 VPUs, the AI-1000-MV is ideal for AI . . .

  • Axiomtek eBOX800-900-FL

    Key Features

    • IP67 Rated for Outdoor Use.
    • 256 CUDA Cores.
    • -30 to +60°C Operating Temp.
    • AC Input with Isolation.
    • M12 LAN with PoE.
    • WiFi/BT and Optional 4G.

    Quick Overview

    The eBOX800-900-FL is a fully IP67 rated fanless rugged edge computer designed for outdoor use and is powered by the NVIDIA® Jetson™ TX2 GPGPU for high-end processing performance.

  • Axiomtek eBOX560-900-FL

    Key Features

    • NVIDIA® JETSON TX2
    • AI Computing Performance
    • GPU Accelerated Processing
    • Compact w/ NVMe Support
    • Intelligent Edge Applications
    • JetPack Support

    Quick Overview

    The Axiomtek eBOX560-900-FL employs a NVIDIA Jetson™ TX2 module which has a powerful 64-bit ARM A57 processor; a 256 CUDA cores with NVIDIA® Pascal™ GPU Architecture; 8GB of LPDDR4 memory; . . .