Lanner EAI-I351 is a rugged edge AI computer built around the NVIDIA Jetson Thor platform, featuring a 100GbE QSFP28 port for high-bandwidth networking and 8x GMSL2 camera inputs for low-latency vision processing.
The system supports up to 128 GB of 256-bit LPDDR5X memory, features up to four 25GbE lanes via a QSFP28 port, a 5GbE RJ45 port, HDMI 2.0, four USB 3.2 Gen1 ports, two RS232/422/485 serial interfaces with optional CANBus, digital I/Os, and audio interfaces. Three expansion sockets are offered with an M.2 NVMe slot, an M.2 E-Key for Wi-Fi/Bluetooth, and an M.2 B-Key for 4G LTE/5G cellular with dual Nano-SIM support. Designed for industrial deployments, the embedded computer can operate in a –25°C to 70°C temperature range and takes 24V/48V DC power input. It targets robotics, smart manufacturing, and autonomous systems such as collaborative robots, AMRs, and machine-vision-based factory automation.
Lanner EAI-I351 specifications:
- Supported system-on-module – NVIDIA Jetson Thor T5000 (EAI-I351A) or Jetson Thor T4000 (EAI-I351B)
- Memory – Up to 128GB (EAI-I351A), 64 GB (EAI-I351B) 256-bit LPDDR5X (273 GB/s bandwidth)
- Storage – M.2 M-Key 2280 NVMe SSD slot (default 512GB included)
- Display – HDMI 2.0 port
- Camera – 8x GMSL2 deserializers for automotive cameras
- Audio – 2x 3.5 mm audio jacks (Mic In and Line Out)
- Networking
- QSFP28 cage (configurable as 4x 25GbE for EAI-I351A or 3x 25GbE for EAI-I351B)
- 5GbE RJ45 port
- Optional Wi-Fi/Bluetooth via M.2 E-Key module
- Optional 4G LTE/5G via M.2 B-Key module and 2x Nano-SIM slots (dual SIM support)
- 4x antenna holes for 4G LTE/5G
- 2x antenna holes for WiFi and Bluetooth
- USB – 4x USB 3.2 Gen 1 Type-A ports (one could be switched as recovery)
- Serial
- 2x DB9 ports with RS232/422/485
- CAN Bus (Optional)
- Expansion
- M.2 M-Key PCIe socket for NVMe storage
- M.2 E-Key 2230 socket for WiFi/Bluetooth.
- M.2 B-Key 3042/3052 socket for LTE/5G (with 2x Nano-SIM slots)
- 4× DI + 4× DO ports on the backside
- Security – Onboard TPM 2.0
- Misc
- Watchdog Timer
- RTC with battery
- Power and Reset buttons
- Cooling – Passive heatsink with dual blower fans
- Mounting – Wall mount
- Power Supply – 24V/48V DC input via 3-pin terminal block
- Dimensions – 201 x 180 x 95 mm
- Temperature Range – -25°C to 70°C
- Certifications – CE, UKCA, FCC Class A, RoHS, UL/CB, IEC 62368-1
The system supports the NVIDIA AI software stack, including the JetPack 7.0 SDK, Ubuntu 24.04 LTS (Kernel 5.15), so it should have support for frameworks such as NVIDIA Isaac for robotics and Metropolis for vision AI.
The Lanner EAI-I351 joins other NVIDIA Jetson Thor-based systems such as the Firefly EC-ThorT5000, the AAEON BOXER-8742AI, and the ASUS IoT PE3000N, which typically focus on standard 2.5GbE or 10GbE connectivity and camera input. The Lanner Edge AI computer is designed to handle far more data-intensive workloads thanks to its 100GbE QSF28 port, in addition to running AI inference on the Jetson Thor T5000/T4000 Blackwell GPU.
At the time of writing, the company has not released public pricing information for the EAI-I351A or EAI-I351B variants, and you would have to contact the company directly for any quotation. More details can be found on the product page.
Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.
