Anonymous
Mar 31, 2026
Rating: 5/5
Exceeded expectations
The large model support is impressive. I deployed a transformer-based model without issues. Power consumption is also quite reasonable for this level of performance.
Description
Reviews
| Brand | - |
| Category | Robotics / STEM Teaching Tools / Development, Learning, Evaluation & Industrial Control Boards |
| Origin | - |
| Processor | Kendryte K230 RISC-V Dual-Core |
| AI Computing Power | 6 TOPS (INT8) |
| Camera Interface | MIPI CSI 4-Lane Support |
| Memory | 1GB LPDDR4x |
| Storage | MicroSD Card Slot (up to 128GB) |
| Connectivity | Wi-Fi 5 + Bluetooth 5.0 |
| Software Support | CanMV, Python, C/C++ SDK |
| Power Supply | 5V DC via USB Type-C |
| Dimensions | 55mm x 40mm x 12mm |
| Operating Temperature | -20°C to 70°C |
Anonymous
Mar 31, 2026
Rating: 5/5
Exceeded expectations
The large model support is impressive. I deployed a transformer-based model without issues. Power consumption is also quite reasonable for this level of performance.
Anonymous
Mar 29, 2026
Rating: 4/5
Solid hardware, learning curve exists
Hardware quality is excellent and the camera interface works flawlessly. The documentation could be slightly more detailed for beginners, but the community support helps.
Anonymous
Mar 26, 2026
Rating: 5/5
Best RISC-V board for computer vision
Switched from other platforms and the speed difference is noticeable. Python support via CanMV makes iteration very fast. Highly recommended for developers.
Anonymous
Mar 23, 2026
Rating: 5/5
Perfect for my robot vision system
Integrated Wi-Fi and strong AI processing make this ideal for autonomous robots. The form factor is compact enough to fit easily into my chassis.
Anonymous
Mar 05, 2026
Rating: 4/5
Great for university projects
Using this for my final year project on smart surveillance. It handles multiple streams well. Only wish it came with a case included.
Anonymous
Mar 02, 2026
Rating: 5/5
Incredible performance for the price
The 6 TOPS computing power is no joke. I was able to run complex object detection models smoothly using CanMV. Great board for prototyping AI vision projects.
Q: Is the source code for the pre-installed demos open source?
A: Yes, most example codes and drivers provided in the CanMV environment are open source and available on our official GitHub repository.
Q: Can I power this board using a power bank?
A: Absolutely. As long as your power bank provides a stable 5V/2A output via USB-C, it will work perfectly.
Q: Is there a GPIO header available for connecting external sensors?
A: Yes, the board includes a standard 40-pin GPIO header compatible with many common sensors and peripherals.
Q: Does this board support running YOLOv8 models?
A: Yes, the K230's 6 TOPS NPU supports YOLOv8 and other popular object detection models when optimized for the Kendryte SDK.
Q: What is the maximum resolution supported by the camera interface?
A: The MIPI CSI interface supports up to 4K resolution at 30fps, depending on the specific camera sensor module used.