ASUS unveiled Tinker Edge T & CR1S-CM-A SBCs based on Google Coral Edge TPU system-on-module featuring both NXP i.MX 8M processor and Google Edge TPU co-processor for AI acceleration in May 2019, but at the time none of the boards were available.
But earlier this month, ASUS officially announced the board, and it can now be purchased on various sites including Provantage (~$168.35) and Physical Computing (21,600 JPY ~ $200). It is also listed on Connection for about $198 but currently out of stock.
- Edge TPU module
- SoC – NXP i.MX 8M quad-core Arm Cortex-A53 processor with Arm Cortex-M4F real-time core, GC7000 Lite 3D GPU
- ML accelerator – Google Edge TPU coprocessor delivering up to 4 TOPS
- System Memory – 1 GB LPDDR4 RAM
- Storage – 8 GB eMMC Flash memory
- Wireless Connectivity – Wi-Fi 2×2 MIMO (802.11b/g/n/ac 2.4/5GHz) Bluetooth 4.2
- Storage – MicroSD card slot
- Networking – Gigabit Ethernet port (via RTL8211F-CG)
- Video Output – MIPI DSI connector, and HDMI output up to 4K with CEC support
- Camera I/F – 2x MIPI CSI 2 interfaces for stereoscopic camera applications
- USB – 2x USB 3.2 gen1 ports, 1x USB-C 3.2 gen1 port
- Expansion – 40-pin Raspberry Pi compatible color-coded header with GPIO, I2C, PWM, UART, SPI, I2S, etc…
- Misc – Programmable LEDs
- Power Supply – 12-19V DC input (up to 45 Watts)
- Dimensions – 85x56mm
The board runs Debian-based Mendel OS Linux used by other Google Coral SBCs, which you could download via the Drivers & Utility section of the download page. The Edge TPU delivers 4 TOPS using only 0.5 watts per unit of computation and is optimized for TensorFlow Lite models. ASUS Tinker Edge T is ideal for computer vision applications such as depth measurement, smart vending machine QR code payment systems, and interactive advertising.