Ask AI Anything

EC5350
High-Performance
AI Edge Inference Computer

EC5350 is a 67 TOPS AI edge inference computer powered by NVIDIA Jetson Orin Nano, built for industrial deployments with rich I/O, flexible expansion, and cloud management.

EC5350
High-Performance
AI Edge Inference Computer

EC5350 is a 67 TOPS AI edge inference computer powered by NVIDIA Jetson Orin Nano, built for industrial deployments with rich I/O, flexible expansion, and cloud management.

PHOTO

Ultra-High-Performance Industrial AI Edge Inference Platform

NVIDIA Jetson Orin Nano platform

Supports the Jetson Orin Nano module to meet moderate AI computing requirements.

Powerful AI inference performance

Delivers up to 67 TOPS AI performance for advanced edge intelligence.

Rich industrial interfaces

Provides interfaces including PoE, Ethernet, serial ports, CAN, USB, HDMI, and DI/DO.

Stable multi-network connectivity

Supports 5G/4G, Ethernet, and Wi-Fi with multi-link redundancy.

Industrial-grade reliability

Fanless design with industrial EMC compliance and wide temperature support.

Cloud-based device management

Integrated with DeviceLive for remote device and AI application management.

  • Core Technical Specifications
    Open Platform Linux (JetPack 5.1 and above)
    AI Module Jetson Orin Nano 8GB / Orin NX 16GB
    AI Performance Up to 40 TOPS (EC5350) / 100 TOPS (EC5550)
    Data Acquisition Modbus RTU/TCP, EtherNet/IP, OPC UA, DNP3.0, IEC 61850-MMS, BACnet, CNC
    Storage Built-in 128GB NVMe, microSD support
    Security TPM2.0, Secure Boot
    Cloud Management DeviceLive cloud parameter, container, app, and firmware lifecycle management
    Interfaces 2×GE, 2×RS-232/485/422, DI/DO, CAN FD, USB3.2, HDMI, audio, GMSL2
    Cellular Network 5G NR / LTE Cat.6 (model-dependent)
    Network Features Dual-SIM backup, multi-level link detection, auto-redial
    Power Input 9~36V DC, polarity reversal protection
    Protection Rating IP30
  • Hardware Platform
    CPU EC5350: ARM Cortex-A78AE, 6 cores, TDP up to 15 W, 1.5 GHz; EC5550: ARM Cortex-A78AE CPU, 8 cores, TDP up to 25 W, 2 GHz
    GPU 1024-core NVIDIA Ampere GPU with 32 Tensor Cores
    NPU AI acceleration up to 40 TOPS (EC5350) / 100 TOPS (EC5550)
    RAM 8GB (EC5350) / 16GB (EC5550)
    FLASH 1 x M.2 NVMe M-Key 2280 (128GB built-in)
  • Connectivity & Interfaces
    Ethernet Ports 2×10/100/1000 Mbps, PoE PSE 15W per port
    I/O Ports 4×DI + 4×DO
    Serial Ports 2×RS-232/RS-485/RS-422 (DB9)
    CAN 1×CAN FD
    Buttons 1×Recovery Button, 1×Reset Button
    SIM Card Holders 2×standard SIM
    LED Indicators 1×Power, 1×Status, 4×User
    USB 6×USB3.2 Gen2 + 1×OTG Type-C
    microSD (microSD) microSD support
    MIC 3.5 mm microphone audio jack
    Audio 3.5 mm type line-out
    GMSL 2-channel GMSL2.0 (FAKRA)
    Expansion Interfaces 1×M.2 B-Key (LTE/5G) 1×M.2 E-Key (Wi-Fi/BT) M.2 NVMe M-Key 2280
    HDMI 1×HDMI2.0 (up to 3840×2160@60Hz)
    Wi-Fi 802.11b/g/n/ac (RTL8822CE-CG)
    Bluetooth BLE5.0
    GPS Supported (cellular module required)
  • Power & Power Consumption
    Input Voltage DC 9~36V
    Power Interface DC input with polarity reversal protection
    Typical Value (OS Idle State) 10W
    Maximum Value (Full Load) 60W
  • Mechanical Specifications
    Product Dimensions 180 × 160 × 60 mm (7.09 × 6.3 × 2.36 in)
    Mounting Method (Wall-mount Optional) DIN-rail (default) / wall-mount
    Protection Rating IP30
    Enclosure & Heat Dissipation Metal housing, fanless design
    TPM TPM2.0
  • Environment & Certifications
    Storage Temperature -40 °C ~ 85 °C (-40 °F ~ 185 °F)
    Operating Temperature -20 °C ~ 60 °C (-4 °F ~ 140 °F)
    Environmental Humidity 5~95% RH (non-condensing)
    Physical Characteristics IEC60068-2-27 shock resistance IEC60068-2-6 vibration resistance IEC60068-2-32 drop resistance
    EMC Standard EN61000-4-2, level 3, Static EN61000-4-3, level 3, Radiation Electric Field EN61000-4-4, level 3, Pulsed Electric Field EN61000-4-5, level 3, Surge EN61000-4-6, level 3, Conducted Disturbance Immunity EN61000-4-8, Power Frequency Field Resistance, horizontal / vertical 400A/m (>level 2) EN61000-4-12, level 3, Shock Wave Resistance
  • Operating System
    Operating System Linux (JetPack 5.1 and above)
  • Network Features
    Network Access 5G or LTE Cat.6 (model-dependent), Ethernet
    Network Standards 5G, LTE Cat.6 (different models for different networks)
  • Security
    Secure Boot Supported
  • Reliability
    Link Detection Multi-level link detection with auto-redial
    Built-in Watchdog Embedded watchdog self-recovery
    Dual-SIM Switchover Supported
  • Data Acquisition Protocols (DSA)
    Industrial Protocols Modbus RTU Master/Slave, Modbus TCP Master/Slave, EtherNet/IP, ISO on TCP, OPC UA Client/Server, Mitsubishi MC 3C/3E/3C OverTCP, Mitsubishi CPU Port, FINSUDP, HostLink, PPI
    Power Protocols DLT645-2007, IEC101/104, DNP3.0, IEC 61850-MMS
    Other Protocols BACnet, CNC
  • Network Management
    Upgrade Method Supports patent upgrade mechanism, local or remote firmware upgrade
    Log Functions Local/remote logs with power-off preservation
    Remote management DeviceLive / HTTP / HTTPS / SSH remote management
    DeviceLive Cloud Supports cloud-based parameter configuration, container management, application and firmware management
Fetching resources...

Standard package*

  • EC5350 AI Edge Computer *1
  • 4G Antenna *1
  • 5G Antenna *4
  • Wi-Fi Antenna *2
  • Ethernet Cable *1
  • Optional accessories
  • Power Adapter *1
  • AC Cable *1
  • Panel Mounting Kit *1

* Standard package contents vary by standard order codes.

Contact us directly to learn more about our packaging options.

Specifications
  • Core Technical Specifications
    Open Platform Linux (JetPack 5.1 and above)
    AI Module Jetson Orin Nano 8GB / Orin NX 16GB
    AI Performance Up to 40 TOPS (EC5350) / 100 TOPS (EC5550)
    Data Acquisition Modbus RTU/TCP, EtherNet/IP, OPC UA, DNP3.0, IEC 61850-MMS, BACnet, CNC
    Storage Built-in 128GB NVMe, microSD support
    Security TPM2.0, Secure Boot
    Cloud Management DeviceLive cloud parameter, container, app, and firmware lifecycle management
    Interfaces 2×GE, 2×RS-232/485/422, DI/DO, CAN FD, USB3.2, HDMI, audio, GMSL2
    Cellular Network 5G NR / LTE Cat.6 (model-dependent)
    Network Features Dual-SIM backup, multi-level link detection, auto-redial
    Power Input 9~36V DC, polarity reversal protection
    Protection Rating IP30
  • Hardware Platform
    CPU EC5350: ARM Cortex-A78AE, 6 cores, TDP up to 15 W, 1.5 GHz; EC5550: ARM Cortex-A78AE CPU, 8 cores, TDP up to 25 W, 2 GHz
    GPU 1024-core NVIDIA Ampere GPU with 32 Tensor Cores
    NPU AI acceleration up to 40 TOPS (EC5350) / 100 TOPS (EC5550)
    RAM 8GB (EC5350) / 16GB (EC5550)
    FLASH 1 x M.2 NVMe M-Key 2280 (128GB built-in)
  • Connectivity & Interfaces
    Ethernet Ports 2×10/100/1000 Mbps, PoE PSE 15W per port
    I/O Ports 4×DI + 4×DO
    Serial Ports 2×RS-232/RS-485/RS-422 (DB9)
    CAN 1×CAN FD
    Buttons 1×Recovery Button, 1×Reset Button
    SIM Card Holders 2×standard SIM
    LED Indicators 1×Power, 1×Status, 4×User
    USB 6×USB3.2 Gen2 + 1×OTG Type-C
    microSD (microSD) microSD support
    MIC 3.5 mm microphone audio jack
    Audio 3.5 mm type line-out
    GMSL 2-channel GMSL2.0 (FAKRA)
    Expansion Interfaces 1×M.2 B-Key (LTE/5G) 1×M.2 E-Key (Wi-Fi/BT) M.2 NVMe M-Key 2280
    HDMI 1×HDMI2.0 (up to 3840×2160@60Hz)
    Wi-Fi 802.11b/g/n/ac (RTL8822CE-CG)
    Bluetooth BLE5.0
    GPS Supported (cellular module required)
  • Power & Power Consumption
    Input Voltage DC 9~36V
    Power Interface DC input with polarity reversal protection
    Typical Value (OS Idle State) 10W
    Maximum Value (Full Load) 60W
  • Mechanical Specifications
    Product Dimensions 180 × 160 × 60 mm (7.09 × 6.3 × 2.36 in)
    Mounting Method (Wall-mount Optional) DIN-rail (default) / wall-mount
    Protection Rating IP30
    Enclosure & Heat Dissipation Metal housing, fanless design
    TPM TPM2.0
  • Environment & Certifications
    Storage Temperature -40 °C ~ 85 °C (-40 °F ~ 185 °F)
    Operating Temperature -20 °C ~ 60 °C (-4 °F ~ 140 °F)
    Environmental Humidity 5~95% RH (non-condensing)
    Physical Characteristics IEC60068-2-27 shock resistance IEC60068-2-6 vibration resistance IEC60068-2-32 drop resistance
    EMC Standard EN61000-4-2, level 3, Static EN61000-4-3, level 3, Radiation Electric Field EN61000-4-4, level 3, Pulsed Electric Field EN61000-4-5, level 3, Surge EN61000-4-6, level 3, Conducted Disturbance Immunity EN61000-4-8, Power Frequency Field Resistance, horizontal / vertical 400A/m (>level 2) EN61000-4-12, level 3, Shock Wave Resistance
  • Operating System
    Operating System Linux (JetPack 5.1 and above)
  • Network Features
    Network Access 5G or LTE Cat.6 (model-dependent), Ethernet
    Network Standards 5G, LTE Cat.6 (different models for different networks)
  • Security
    Secure Boot Supported
  • Reliability
    Link Detection Multi-level link detection with auto-redial
    Built-in Watchdog Embedded watchdog self-recovery
    Dual-SIM Switchover Supported
  • Data Acquisition Protocols (DSA)
    Industrial Protocols Modbus RTU Master/Slave, Modbus TCP Master/Slave, EtherNet/IP, ISO on TCP, OPC UA Client/Server, Mitsubishi MC 3C/3E/3C OverTCP, Mitsubishi CPU Port, FINSUDP, HostLink, PPI
    Power Protocols DLT645-2007, IEC101/104, DNP3.0, IEC 61850-MMS
    Other Protocols BACnet, CNC
  • Network Management
    Upgrade Method Supports patent upgrade mechanism, local or remote firmware upgrade
    Log Functions Local/remote logs with power-off preservation
    Remote management DeviceLive / HTTP / HTTPS / SSH remote management
    DeviceLive Cloud Supports cloud-based parameter configuration, container management, application and firmware management
Fetching resources...

Standard package*

  • EC5350 AI Edge Computer *1
  • 4G Antenna *1
  • 5G Antenna *4
  • Wi-Fi Antenna *2
  • Ethernet Cable *1
  • Optional accessories
  • Power Adapter *1
  • AC Cable *1
  • Panel Mounting Kit *1

* Standard package contents vary by standard order codes.

Contact us directly to learn more about our packaging options.

DeviceLive

IoT Device Management Platform

Device management, remote monitoring, edge app management, and remote maintenance to help industrial enterprises build intelligent edge networks.

DeviceLive

Frequently Asked Questions

What AI workloads is the EC5350 designed for?

The EC5350 is an NVIDIA Jetson-based AI edge computer built around the NVIDIA Jetson Orin Nano 8 GB (6-core ARM Cortex-A78AE @ 1.5 GHz, 1024-core NVIDIA Ampere GPU with 32 Tensor Cores), delivering up to 67 TOPS of AI compute. It runs Linux (JetPack 5.1+) with Docker container support. Industrial I/O: 2× Gigabit Ethernet PoE PSE (IEEE 802.3af, 15 W per port), 2× RS-232/485/422 (DB9, software-configurable), 4× DI + 4× DO, 1× CAN FD, 2-ch GMSL 2.0 (FAKRA), 6× USB 3.2 Gen 2 + USB-C OTG, 1× HDMI 2.0 (up to 4K@60 Hz), Wi-Fi 5 + BLE 5.0, 2× standard SIM, 128 GB NVMe storage built in, TPM 2.0. Power: DC 9–36 V, 10 W idle / 60 W peak. Form factor: 180 × 160 × 60 mm metal chassis, IP30, DIN-rail or wall-mount, −20 to +60 °C. Cellular options: 5G NR (NRQ3), 4G LTE Cat 6 (FQ09), or no-cellular (EN00).

The EC5350 is an NVIDIA Jetson-based edge computer running JetPack 5.1 with HDMI 2.0 + USB 3.2 — three access methods are supported.

Direct (primary): Connect HDMI display + USB keyboard/mouse. Power on, select the System User account on the login screen, and enter the nameplate password. Use the JetPack Linux desktop directly.

Remote — SSH: Connect to the default ETH2 IP 192.168.4.100 using an SSH client (MobaXterm, PuTTY). Log in with the System User credentials from the nameplate.

Remote — IEOS web: Open https://192.168.4.100:9100 (HTTPS only, port 9100). Log in as username adm with the nameplate password.

The EC5350 runs NVIDIA JetPack 5.1+ on the Jetson Orin Nano 8 GB module, with Docker container support, and is compatible with the NVIDIA AI ecosystem. Up to 67 TOPS of AI compute is available for edge inference workloads.

The EC5350 runs JetPack with Docker container support. For remote container lifecycle management, enroll the EC5350 in DeviceLive — cloud-based parameter configuration, container management, and application and firmware management are exposed in the portal, along with remote batch management of edge AI applications.

You May Also Like