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.

  • Nvidia Jetson

    Power efficient AI-at-the-edge inference systems, boards and modules based on Nvidia Jetson TX2, Nano & Xavier accelerators.

  • Intel Movidius

    Power efficient AI-at-the-edge inference systems and add-on cards based on Intel Movidius accelerators.

  • GPU + x86 Industrial Computer

    High performance AI inference systems based on Nvidia GeForce and Quadro graphics cards and latest generation Intel CPUs.

  • EGX-MXM-P2000

    Key Features

    • MXM 3.1 Type A Form Factor
    • 768 NVIDIA CUDA Cores
    • 2.3 TFLOPS SP Performance
    • 4GB GDDR5 Memory
    • 96GB/s Memory Bandwidth
    • Supports Up to 4 FHD Displays

    Quick Overview

    ADLINK’s EGX-MXM-P2000 Embedded MXM GPU Modules features advanced NVIDIA Quadro GPU with NVIDIA Pascal™ Architecture technology in MXM 3.1 Type A form factor. The EGX-MXM-P2000 has 768 NVIDIA CUDA cores . . .

  • EGX-MXM-P1000

    Key Features

    • MXM 3.1 Type A Form Factor
    • 512 NVIDIA CUDA Cores
    • 1.8 TFLOPS SP Performance
    • 4GB GDDR5 Memory
    • 96GB/s Memory Bandwidth
    • Supports Up to 4 FHD Displays

    Quick Overview

    The EGX-MXM-P1000 features advanced NVIDIA Quadro GPU with NVIDIA Pascal™ Architecture technology in MXM 3.1 Type A form factor. The EGX-MXM-P1000 has 512 NVIDIA CUDA cores and a peak single-precision . . .

  • Key Features

    • JetsonTM TX2 / JetsonTM Xavier NX
    • Up to 5 MP Image Resolution
    • Four Type Colour Sensors
    • DIO, Serial & LAN Connectivity
    • Micro SD For External Storage
    • IP67 Certified

    Quick Overview

    ADLINK’s NEON-2000 Series of the NVIDIA® Jetson™-based industrial AI cameras integrate the Jetson™ Xavier NX or Jetson™ TX2, an image sensor, an optimized OS, and broad I/O for vision applications . . .

  • 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

    • Movidius™ Myriad™ X VPU
    • Intel Atom® E3930 CPU
    • Up to 5 MP Image Resolution
    • FPGA-based Digital I/O
    • Four Type Colour Sensors
    • DIO, Serial & LAN Connectivity
    • Micro SD For External Storage

    Quick Overview

    ADLINK’s NEON-1000-MDX Series of industrial AI smart cameras equips the Intel Atom® E3930 CPU and Movidius™ Myriad™ X VPU and a range of image sensors, providing users the flexibility to . . .

  • 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 ROScube-X Series 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.

  • 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; . . .

  • IEI Mustang-V100-MX8

    Key Features

    • 8 x Intel Myriad X VPUs
    • <30W Power Consumption
    • OpenVINO­ Toolkit Support
    • Multi Card Support Per System
    • Low Latency
    • AI Edge Computing Ready

    Quick Overview

    The IEI Mustang-V100-MX8 is a small form factor, low power consumption, and low-latency Intel Movidius based PCIe card for inference at the edge computing solutions.