- Google Edge TPU ML accelerator
- NXP i.MX 8M SoC (Quad-Core)
- 1 GB LPDDR4x
- 1x GbE PoE/PD LAN port
- Operating temp.: -5 °C ~ 50 °C
- Dimensions: 175.8 x 100 x 39mm
FEATURES
Get your inquiry

Product: BOXER-8521AI
SKU:
Request callback

Product: BOXER-8521AI
SKU:
Description
BOXER-8521AI – AI@Edge Embedded Platform
Winner of the 2021 Taiwan Excellence Award, the BOXER-8521AI features installation and connectivity flexibility. The BOXER-8521AI features a PoE-PD port that allows the system to be installed farther away from the power source and enables Internet connectivity and remote monitoring of the system via a single cable. By using both the PoE-PD port and the DC input, the system can continue to operate even if one of the two power supplies is interrupted.
The BOXER-8521AI enables AI edge computing thanks to the Google Edge TPU system-on-module (SoM) with a robust chassis and flexible I/O workload. The Google Edge TPU combines the NXP i.MX 8M SoC (Quad Cortex-A53, Cortex-M4F) with the Google Edge TPU coprocessor to achieve speeds of up to 4 TOPS at an energy-efficient 2 TOPS per watt.
Quickly develop and train AI models
Thanks to the Google Edge TPU, developers and users deploying the BOXER-8521AI have access to Google’s AutoML Vision Edge training software suite. This innovative software helps developers quickly develop and train AI models by leveraging Google’s extensive cloud services and then exporting the model to the BOXER-8521AI and the Google Edge TPU. The system supports TensorFlow Lite, a framework that enables more efficient models and better system performance and processing speed.
The BOXER-8521AI is ruggedly built with a fanless design to keep out dust and contaminants, enabling longer-term and reliable operation. In addition, the system can operate at temperatures from -5°C to 50°C without loss of performance. The BOXER-8521AI is equipped with flexible I/O features that include COM, HDMI, two USB3.2 Gen 1 and two USB2.0 ports. It also has a 40-pin multi-I/O port for connecting additional sensors and controllers, such as cameras, temperature sensors and others.
Specifications
Product: BOXER-8521AI | |
---|---|
AI Accelerator | Google Edge TPU ML accelerator coprocessor |
Processor | NXP i.MX 8M SoC (Quad-Core Cortex-A53, plus Cortex-M4F) |
RAM | 1 GB LPDDR4x |
Storage | 8GB eMMC |
I/O | 1x HDMI 2.0a 2x USB Type A for 3.2 Gen 1 2x USB Type A for 2.0 2x RJ-45 for PoE/PD (802.3at) 1x 12V DC (DC jack w/ lockable) 1x Mic-in 1x Line-out 1x 40-pin I/O (GPIO/I2C/SAI/SPI/UART/PWM) 1x DB-9 for RS-232/485 1x OS flash port (Micro-USB) 1x MicroSD slot |
Expansion | – |
Power Requirement | PoE/PD (802.3at) 1x 12V DC (DC jack w/ lockable) |
Mounting | Wallmount kit |
Dimensions | 175.8 x 100 x 39 mm |
Weight | 1.05 kg (gross) 0.58 kg (net) |
Operating Temperature | -5°C ~ 50°C |
Storage Temperature | -40°C ~ 85°C |
Humidity | 5 ~ 95% @ 40°C, non-condensing |
Vibration | Random, 3.5Grm / 5 ~ 500Hz |
Shock | 50G peak acceleration (11 msec. duration, eMMC, microSD) |
Certification | CE/FCC Class A |
Accessories & Related products
-
BOXER-8253AI
- NVIDIA®Jetson™ Xavier NX
- 6-Core ARM v8.2 64-bit
- 8 GB LPDDR4x
- 2x GbE PoE/PSE LAN ports
- Operating temp.: -15 °C ~ 55 °C
- Dimensions: 180 x 136 x 61,1 mm
-
BOXER-8240AI
- ARM v8.2 64bit CPU, 8-core
- 32 GB 256-Bit LPDDR4
- NVIDIA® AGX Xavier Accelerator
- 4x GbE PoE for IP-Cameras
- Operating temp.: -10 °C ~ 55 °C
- Dimensions: 210 x 164 x 60mm
-
BOXER-8251AI
- ARM® Carmel® V8.2 64bit CPU
- 8 GB LPDDR4
- NVIDIA® Xavier NX Accelerator
- 1x HDMI, 1x GbE, 1x COM, 4x USB
- Operating temp.: -20 °C ~ 50 °C
- Dimensions: 88 x 75 x 39mm