SolidRun’s HummingBoard 8P Edge AI combines an NXP i.MX 8M Plus system-on-module with a Hailo-8 M.2 accelerator to run AI inference locally, with camera, video, display and networking connections aimed at embedded vision projects. SolidRun advertises up to 28 combined TOPS, but that is a vendor-stated figure—not an independent performance benchmark.
What the HummingBoard 8P Edge AI is
The HummingBoard 8P Edge AI is a compact embedded-computing platform built around SolidRun’s HummingBoard carrier and an NXP i.MX 8M Plus system-on-module (SOM). A Hailo-8 accelerator connects over M.2 PCIe, adding a dedicated processor for supported neural-network inference. The combination is intended for edge applications such as camera analytics, object detection and video streams, where processing can happen on the device rather than relying on a cloud service.
The host processor and accelerator have distinct roles: the i.MX 8M Plus runs the operating system and application, while workloads compiled for Hailo can use the Hailo-8. Having both does not mean every model or operation automatically uses both processors.
How much AI performance does it claim?
SolidRun specifies up to 26 TOPS from the Hailo-8 and describes the system as delivering up to 28 TOPS combined with the i.MX 8M Plus. CNX Software reports the i.MX 8M Plus NPU at 2.3 TOPS, a different figure from the 2 TOPS SolidRun uses in its combined total. These are source-attributed throughput specifications, not a single independently verified system benchmark. ( SolidRun launch announcement; CNX Software report )
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- POWERFUL COMPUTING: Advanced single board computer featuring high-speed LPDDR5 memory for superior processing capabilities and edge AI computing performance
- CONNECTIVITY: Multiple USB ports, HDMI output, and Ethernet connectivity provide versatile interface options for various applications
- COMPACT DESIGN: Space-efficient circuit board layout integrates powerful computing components in a single compact form factor
- DEVELOPMENT READY: Ideal platform for edge AI development, programming, and prototyping with comprehensive hardware interfaces
- EXPANDABILITY: Features multiple GPIO pins and standard connectors enabling extensive hardware expansion possibilities
TOPS is a theoretical operations-per-second rate, not a prediction of frames per second, latency, accuracy or performance on a particular model. Those outcomes depend on the model, resolution, preprocessing, software stack and workload. No independent test results are established here, so treat the TOPS figures as specifications rather than expected real-time rates.
Specifications and connections
| Area | HummingBoard 8P Edge AI details |
|---|---|
| Host processor | NXP i.MX 8M Plus, quad-core Arm Cortex-A53 up to 1.8GHz; integrated NPU. CNX reports 2.3 TOPS for the NPU. |
| AI accelerator | Hailo-8 M.2 PCIe module, up to 26 TOPS; SolidRun lists 2.5W typical accelerator consumption. |
| Memory and storage | Up to 8GB LPDDR4, up to 128GB eMMC, and microSD support. |
| Camera and display | MIPI-CSI camera connection, HDMI output, and two USB 3.0 ports. |
| Networking | Dual Gigabit Ethernet with PoE support, plus Wi-Fi 5 and Bluetooth. |
| Other connections and controls | Audio codec, micro-USB debug, reset/configurable button, LEDs and RTC. |
| Power and dimensions | 7–36V input; 802.3af Class 0 PoE sink; 100 × 70mm PCBA. SolidRun and CNX report a 10W maximum. |
| Temperature options | Commercial 0–70°C or industrial −40–85°C configurations. |
Specifications and supported configurations are described by SolidRun and CNX Software. The 10W maximum is a reported platform figure, not a guarantee of consumption in every configuration or workload; attached peripherals and operating conditions affect total system draw.
Rank #2
- [High performance] Quad-core ARM SoC up to 1. 8GHz with 3GB RAM- The Tinker Edge R features the Rockchip RK3399Pro SoC and Mali - T764 GPU along with 2GB of Dual Channel LPDDR4 memory for system, 1 GB LPDDR3 memory for NPU and 16GB eMMC flash
- [Gigabit Class networking]Tinker Edge R features a high speed GB LAN port for true Gigabit Class networking throughput along with 3x USB3.2 Gen1 Type-A. It also features onboard Wi-Fi & Bluetooth for robust IoT & Network connectivity
- [Open-source]The board will come with fully open-source kernel and support for multiple APIs, including OpenGL, Vulkan, OpenCL, OpenVX, TensorFlow Lite, Android NN, and Caffe
- [HD Audio & UHD video support] It supports 192/24bit HD Audio playback with automatic Audio jack detection as well as accelerated HD & UHD ( 4K ) video playback and supports HDMI CEC for seamless power on & off configurations
- [WiKi]For more information please refer to the product description, any technical issues after purchase please contact with our tech-support team: click "WayPonDEV" and ask a question. Package Content: 1x Tinker Edge R (3GB+16G eMMC); 2x Wi-FiVBT antenna cable; 1x Stand offset(4xScrew+4xHex); 2x Camera MIPI Convert cable (22P to 15P); 1 x Shielding bag; 1 x Quick start guide
Camera and video use
The MIPI-CSI connection makes the board suitable for camera-oriented designs, while USB 3.0 adds another route for compatible peripherals. SolidRun’s launch materials describe an optional Basler daA3840-30mc 4K/8MP camera capable of up to 30fps. That is the camera’s stated capability, not a measured inference rate for the complete board and AI model.
HDMI provides an output for a monitor or optional touchscreen, useful for a local interface or prototype display. The combination of camera input, local accelerator and display/network outputs supports designs such as visual inspection, license-plate recognition and multi-stream detection. Actual camera compatibility depends on the selected module, driver and software configuration.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Rank #3
- Supports access to online large model platforms and includes Edge Impulse object detection demo for real-time multi-object recognition
- Equipped with Xtensa dual-core LX7 processor (up to 240MHz), 8MB PSRAM, 16MB Flash, and dual-mode WF + BT LE
- Dual-microphone array with noise reduction and echo cancellation for high-quality voice processing
- Integrated audio input and output module, supporting AI speech interaction and voice recognition applications
- Onboard camera interface (DVP) and SPI / QSPI display interface for image capture, recognition, and external display connection
Software and documented demos
SolidRun lists TensorFlow, TensorFlow Lite, Keras, PyTorch and ONNX among the supported model-framework ecosystem. The board also has Linux BSP resources and Debian, Buildroot and Yocto materials. Framework support does not mean an unmodified model can be sent directly to the Hailo accelerator: deployment may require model conversion, quantization, compilation and compatible runtime components.
The documented demonstration workloads include:
- Object detection
- License-plate recognition
- Multi-stream detection
These examples indicate the kinds of vision tasks the platform targets; they do not establish a specific throughput, latency or accuracy for a customer’s model. Consult the current SolidRun product and software information for applicable BSP and demo resources.
Rank #4
- 30-in-1 No-Solder Sensor Board, Plug and Play: Integrates 30 functional sensors including temperature & humidity, ultrasonic ranging, gas and motion sensors. Innovative common board design requires no soldering or complex wiring, and comes with a full set of accessories like 128G SD card, adapter board and acrylic mounting plates for zero-threshold experiments
- 8MP Gimbal Camera & Dual Servos for Professional Visual AI: The Starter Kit is equipped with an IMX219 8MP monocular camera and a dual-servo gimbal, supporting face and target tracking, and is ideal for AI edge computing scenarios such as intelligent monitoring, robot navigation, and automated recognition
- 38 Step-by-Step Python Tutorials, From Beginner to Practical Application: The Jetson Orin Nano Starter Kit comes with 38 well-designed Python tutorials progressing from basic programming to vision practice, covering all key knowledge of sensor control, embedded development and AI visual recognition for both beginners and advanced learners
- 11.6-inch IPS HD Screen & AI Voice Interaction System: Built-in 1366*768 resolution IPS screen eliminates the need for an external monitor, enabling one-device experimentation and visual feedback. The exclusive AI voice interaction system supports intelligent Q&A and voice command control for natural human-computer dialogue
- Rich Expansion Interfaces & Portable All-in-One Design: Features 2x I2C, 1x UART and 2 IO expansion interfaces to meet personalized experiment expansion needs; a custom carrying case integrates all components (11.81×7.87×3.94 inch), allowing AI experiments and demonstrations anytime and anywhere
Launch pricing and what the kit included
At launch, SolidRun stated a $590 starting MSRP for the kit. CNX Software reported a $590 standard kit and an $854 bundle that added the Basler camera and a 7-inch touchscreen. These are launch-era prices, not confirmed current offers. SolidRun described the kit as including BSP, preloaded models, Wi-Fi/Bluetooth, an antenna, heatsink, power adapter and starter hardware.
Before ordering, confirm current price and stock with the seller, along with shipping, taxes, exact SOM memory and storage configuration, included accessories and whether the camera or display is part of the selected package. The launch bundle price should not be assumed to reflect today’s availability or configuration.
Recommended Free Tools
Who should consider it?
The board is a fit to investigate if a project needs local vision inference and benefits from a dedicated Hailo accelerator alongside an embedded Linux host. Its MIPI-CSI, Ethernet, PoE support, HDMI and documented vision demos are relevant to fixed-camera prototypes and embedded installations.
It is less compelling to choose on the basis of TOPS alone. Check that the target model can be deployed to Hailo, that the camera interface and driver suit the project, and that the selected temperature grade, power arrangement and storage are appropriate. For a direct comparison with other edge-AI SBCs, use the same model and deployment pipeline and compare measured throughput, latency, power, connectivity and total configured cost; the stated TOPS figure by itself cannot settle those questions.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
