Mo 62A
Single-Board Computer
Entry-level open-source AI SBC powered by TI AM62A74, delivering 2 TOPS for lightweight edge inference and industrial vision.
FOTO
2 TOPS Open-Source AI SBC For Lightweight Edge Inference
High-Performance Processor
Powered by the Texas Instruments AM62A AI vision processor, featuring a quad-core 64-bit Arm® Cortex®-A53 CPU up to 1.4 GHz
AI Acceleration
Equipped with C7x DSPs and Matrix Multiply Accelerators (MMAs), delivering up to 2 TOPS of deep learning performance
Rich Connectivity
Multi-Modal Interfaces: Gigabit Ethernet, USB 2.0, plus flexible multimedia I/O for cost-effective multi-camera and multi-display systems
Rapid Prototyping
A 40-pin expansion header enables solderless prototyping and broad compatibility with sensors, actuators, and connectivity accessories
-
Technische Kernspezifikationen
AI Accelerator C7x DSP + Deep Learning Accelerator, 2 TOPSAI Runtime TI TIDL, supports TFLite / ONNXBluetooth BLE 4.2CPU 4 × Cortex-A53 @ 1.4 GHzAbmessungen (B × T × H) 85 × 56 mmSchnittstelle 1 × GbE, 4 × USB 2.0, micro HDMI, MIPI CSI-2, 40-pin HATBetriebstemperatur 0 °C ~ +50 °CBetriebssystem Debian 13 (Embedded Linux)Power USB Type-C 5 V / 5 A DC; ≤ 25 WRAM LPDDR4 4 GB (default) / 2 GB / 8 GBSicherheit Secure Boot, TrustZone, OP-TEE, Hardware AES-256W-lan Wi-Fi 5 (802.11ac), dual-band 2.4 / 5 GHz
-
Hardware Platform
AI Accelerator C7x DSP + Deep Learning Accelerator, 2 TOPSCPU TI AM62A74, 4 × Cortex-A53 @ 1.4 GHzISP / Vision On-chip ISP + VPAC (RGB-IR, WDR, LDC)RAM LPDDR4 4 GB (default) / 2 GB / 8 GB
-
Schnittstelle
40-pin Connector GPIO / I²C / SPI / UART / PCM, HAT-compatibleAudio 3.5 mm jack + PCM via 40-pin connectorButton 1 × Reset buttonCamera 1 × 4-lane MIPI CSI-2Debug UART 1 × TTL UARTDisplay 1 × micro HDMIEthernet 1 × Gigabit EthernetFan Connector 1 × 4-pin fan connectorLED PWR, USERLagerung Micro SDUSB 4 × USB 2.0 Type-A
-
Wireless
Antenne Wi-Fi / BLE: on-board snap-on antennaBluetooth BLE 4.2W-lan Wi-Fi 5 (802.11ac), dual-band 2.4 / 5 GHz
-
Power
Stromverbrauch 25 W (MAX)Power input USB Type-C 5 V / 5 A DC
-
Mechanisch
Kühlung Active fan (optional)Abmessungen (B × T × H) 85 × 56 mmGehäuse PCBRTC Support (battery backup)Weight 47 g
-
Umwelt
Betriebstemperatur 0 °C ~ +50 °CLagertemperatur -20 °C ~ +70 °C
-
Betriebssystem
Kernel Linux Kernel 6.12Betriebssystem Debian 13.2 Trixie
-
AI & Vision
AI Runtime TI TIDL, supports TFLite / ONNXCamera Framework V4L2Display Framework DRM / KMSVision SDK TI EdgeAI SDK
-
Network Features
IP Application TCP / UDP, ICMP, DNS, DHCPIP Routing Static routing
-
Sicherheit
Crypto Accelerator Hardware AES-256OP-TEE UnterstützungSicherer Boot UnterstützungTrustZone Unterstützung
-
Development
Languages Python, C/C++Libraries OpenCV, GStreamer, NumPyOpen SDK Supports custom system build by customerPackage Manager apt (Debian)
-
System Management
Debug UART consoleFirmware Upgrade SD card flashRemote Access SSH
-
Product Models
MO-62A-2G 2 GBMO-62A-4G 4 GBMO-62A-8G 8 GB
Standardpaket*
- Mo 62A AI Single Board Computer *1
- Optional accessories
- Power Supply *1
- Wi-Fi-Antenne *1
- RTC Battery *1
- TTL Debug Serial Cable *1
- Fan *1
- Ethernet-Kabel *1
- 32GB SD Card *1
- Micro HDMI to HDMI (MO 62A) *1
- Mini DP to DP (MO 68A) *1
* Standard package contents vary by standard order codes.
Kontaktieren Sie uns Um mehr über unsere Verpackungsoptionen zu erfahren, wenden Sie sich bitte direkt an uns.
DeviceLive
IoT-Geräteverwaltungsplattform
Device management, remote monitoring, edge app management, and remote maintenance to help industrial enterprises build intelligent edge networks.
Häufig gestellte Fragen
What does the MO-62A offer?
The MO-62A is a 2-TOPS AI single-board computer for on-device vision inference at the edge. Key specs:
| — | — |
| Compute | 4× Cortex-A53 @ 1.4 GHz + C7x DSP + 2-TOPS Deep Learning Accelerator |
| Vision pipeline | On-chip ISP + VPAC (RGB-IR, WDR, LDC); 1× 4-lane MIPI CSI-2 |
| RAM | LPDDR4, 2 GB / 4 GB (default) / 8 GB SKUs ( MO-62A-2G/-4G/-8G ) |
| Betriebssystem | Debian Linux |
| Konnektivität | 1× Gigabit Ethernet, Wi-Fi 5 dual-band, BLE 4.2 |
| Other I/O | 4× USB 2.0 Type-A, micro HDMI, 3.5 mm audio, 40-pin HAT-compatible header, micro SD |
| Sicherheit | Secure Boot, ARM TrustZone, OP-TEE, hardware AES-256 |
| Power / size | USB Type-C 5 V (25 W max), 85 × 56 mm, 47 g |
The 85 × 56 mm board and 40-pin layout are mechanically compatible with standard SBC enclosures and HAT accessories. Typical applications: AI vision boxes, intelligent cameras, defect inspection, and other edge-AI inference terminals. The MO-62A is a developer-oriented SBC managed via SSH and standard Debian tooling — it does not run InHand IEOS or DeviceLive.
How do I flash and boot the MO-62A for the first time?
- Flash the SD card — download the latest
.img.zipfrom the release page (SDK on GitHub:github.com/inhandnet/mo-62a). Use balenaEtcher (Windows / macOS / Linux) orddto write the image to a ≥16 GB Class 10 / UHS-I micro SD card. - Connect peripherals — insert the card, connect a monitor via micro HDMI, plug RJ45 into your network, and optionally attach USB keyboard/mouse and an IMX219 camera ribbon.
- Apply power last via USB Type-C (5 V, ≥3 A). The red Power LED lights immediately. Normal boot is 30–45 s; the first boot adds 1–2 minutes while the root filesystem expands to fill the SD card, after which the board auto-reboots into the XFCE desktop.
- Log in with username
debian, passwordtemppwd— valid for one login only, then you’re prompted to set a new password immediately.
For headless setup, the board acquires DHCP automatically and is reachable at ssh [email protected] (mDNS) or ssh debian@. A 3-pin TTL UART debug connector is also provided (115200 baud, 8N1) for serial-console access.
How do I run AI models on the MO-62A?
Models run through the TI Deep Learning (TIDL) runtime, which accepts TFLite ( .tflite ) and ONNX ( .onnx ) models. The on-chip ISP/VPAC handles RAW→RGB conversion, WDR, and lens correction so the DLA gets a clean input; pre- and post-processing in Python or C/C++ commonly use OpenCV and GStreamer.
At 2 TOPS the MO-62A is sized for image classification, lightweight object detection (e.g., YOLO-Nano variants), OCR, presence/anomaly sensing, and gesture or pose recognition. For multi-stream / high-resolution detection at higher frame rates, step up to a higher-TOPS InHand AI edge computer.
How do I use the 40-pin header on the MO-62A?
The 40-pin HAT-compatible header exposes GPIO, I²C, SPI, UART, PWM, and PCM at 3.3 V logic. Standard SBC HAT accessories mount mechanically — verify electrical compatibility (3.3 V) before connecting.
Pin notes:
- All user pins default to GPIO; alternate functions are enabled via device-tree overlays.
- Pins 27/28 are reserved for the camera I²C bus — they cannot be used as general GPIO.
- The board ships with libgpiod v2.x; the
-cflag is required to specify a chip. Three gpiochips (gpiochip0–gpiochip2) cover the MCU and main domains.
Quick examples:
“ bash`
gpiodetect # list chips
gpioget -c gpiochip2 23 # read pin 11
gpioset -c gpiochip1 39=1 # drive pin 7 high
gpiomon -c gpiochip2 23 # watch edges
i2cdetect -y 2 # scan camera I²C bus
For higher-bandwidth peripherals, use the 4-lane MIPI CSI-2 connector (IMX219 supported via the bundled imx219-preview.sh` script), the micro HDMI for displays, and the four USB 2.0 Type-A ports for storage and adapters.
—