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.

  • Key Features

    • Movidius™ Myriad™ X VPU.
    • Intel® Celeron® J3455 CPU
    • 8GB Pre-installed Memory
    • 2 x Gigabit Ethernet Ports
    • Ultra Compact Fanless Design
    • M.2 A-key Slot Expansion

    Quick Overview

    The IDS-310AI is pre-installed with a Mustang-MPCIE-MX2 AI accelerator card, which includes two Intel® Movidius™ Myriad™ X VPU, to provide a flexible AI inference solution.

  • Key Features

    • IP67 Rated for Outdoor Use.
    • NVIDIA® Jetson Xavier™ NX GPU.
    • High AI Computing Performance
    • 10kV Surge Protection (100 to 240 VAC)
    • Features M12 lockable I/Os.
    • -30 to +50°C Operating Temp.

    Quick Overview

    The AIE800-904-FL is a fully IP67 rated fanless rugged edge computer designed for outdoor use and is powered by the NVIDIA® Jetson Xavier™ NX GPGPU for high-end AI computing performance.

  • Key Features

    • NVIDIA® Jetson AGX Xavier™ GPU.
    • GPU-Accelerated AI Computing.
    • Fanless, Compact & Low Power.
    • Supports M.2 NVMe PCIe x4 SSD
    • -30°C to 50°C Operating Temp.
    • JetPack Supported.

    Quick Overview

    The Axiomtek AIE900-902-FL is a compact and fanless edge AI system with NVIDIA® Jetson AGX Xavier™ series SoM, 32GB 256-Bit LPDDR4x memory onboard and support for Linux based operating systems.

  • Key Features

    • Compact Fanless System
    • Deep Learning Acceleration
    • NVIDIA® Jetson Xavier™ NX
    • 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-211-JNX Edge AI Platform integrates NVIDIA® Jetson Xavier™ NX to accelerate deep learning workloads for object detection, recognition and classification.

  • Key Features

    • AI-enabled Embedded NVR
    • Deep Learning Acceleration
    • NVIDIA® Jetson Xavier™ NX
    • 8 x PoE For IP Cameras
    • 16GB eMMC 5.1 Storage
    • 12V DC Input / AC-DC Board

    Quick Overview

    To deliver Artificial Intelligence (AI) at the edge, ADLINK’s DLAP-301-JNX Edge AI-enabled Embedded NVR integrates NVIDIA® Jetson Xavier™ NX to accelerate deep learning workloads for object detection, recognition and classification.

  • Key Features

    • Compact Fanless System
    • Deep Learning Acceleration
    • NVIDIA® Jetson Nano™
    • Up to 4GB 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-211-Nano Edge Inference Platform integrates NVIDIA® Jetson Nano™ to accelerate deep learning workloads for object detection, recognition and classification.

  • Key Features

    • AI-enabled Embedded NVR
    • Deep Learning Acceleration
    • NVIDIA® Jetson Nano™
    • 8 x PoE For IP Cameras
    • 16GB eMMC Storage
    • 12V DC Input / AC-DC Board

    Quick Overview

    To deliver Artificial Intelligence (AI) at the edge, ADLINK’s DLAP-301-Nano Edge AI-enabled Embedded NVR integrates NVIDIA® Jetson Nano™ to accelerate deep learning workloads for object detection, recognition and classification.

  • Key Features

    • MXM 3.1 Type B Form Factor
    • 3072 NVIDIA CUDA Cores
    • 9.4 TFLOPS peak FP Performance
    • 16GB GDDR6 Memory (256-bit)
    • 448GB/s Memory Bandwidth
    • 110W Maximum Power

    Quick Overview

    The EGX-MXM-RTX5000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type B+ form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. EGX-MXM-RTX5000 . . .

  • Key Features

    • MXM 3.1 Type B Form Factor
    • 1920 NVIDIA CUDA Cores
    • 5.3 TFLOPS peak FP Performance
    • 6GB GDDR6 Memory (192-bit)
    • 336GB/s Memory Bandwidth
    • 80W Maximum Power

    Quick Overview

    The EGX-MXM-RTX3000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type B form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. With . . .

  • Key Features

    • MXM 3.1 Type A Form Factor
    • 896 NVIDIA CUDA Cores
    • 2.6 TFLOPS peak FP32 Performance
    • 4GB GDDR6 Memory (128-bit)
    • 192GB/s Memory Bandwidth
    • 50W Maximum Power

    Quick Overview

    The EGX-MXM-T1000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type A form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. EGX-MXM-T1000 . . .

  • Key Features

    • NVIDIA® Jetson™ TX2 Series GPU.
    • GPU-Accelerated AI Computing.
    • Intelligent Edge Platform.
    • M.2 PCIe & SATA SSD Support.
    • -30°C to 60°C Operating Temp.
    • 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.