Powered by the Rockchip RK3576, an octa-core 64-bit AIOT processor,
supporting the private deployment of large-scale models under the
Transformer architecture.With an external watchdog, it provides
industrial-grade stability, making it an excellent choice for
AI applications requiring local deployment.
The computer is equipped with a powerful NPU, delivering computing power of up to 6 TOPS. This enables advanced intelligent data
processing, speech recognition, and image analysis, effectively fulfilling the AI application demands for
edge computing on a wide range of terminal devices.
RK3576, the new octa-core 64-bit high-performance AIOT processor, features a big.LITTLE architecture (4×A72 +4×A53),
an advanced lithography process, and a frequency of up to 2.2 GHz. It ensures technical support for high-performance computing
and multitasking. With a Mali-G52 MC3 GPU delivering 145G FLOPS, this GPU is capable of supporting efficient heterogeneous
computing to meet the demands of graphics-intensive applications.
This device supports 8K@30fps/4K@120fps decoding (H.265/HEVC, VP9, AVS2, and AV1),
4K@60fps decoding (H.264/AVC), as well as 4K@60fps encoding (H.265/HEVC and H.264/AVC).
It supports HDMI 2.1 (4K@120fps) , and DP 1.4 (4K@120fps).
1000Mbps Ethernet (1 channel), 100Mbps Ethernet (1 channel), 2.4GHz/5GHz dual-band WiFi, Bluetooth 5.0, and 4G LTE
are provided. This powerful network communication capability makes data transmission more stable and faster.
The on-board M.2 interface can be connected with 2242 NVMe/SATA SSD mass storage devices,
which makes it a reality that the device can be easily expanded with TB storage capacity.
HDMI2.1, Gigabit Ethernet, USB3.0, USB2.0, Type-C(OTG / DP1.4), RS232, RS485, CAN, Optocoupler Isolated Input,
realy and more interfaces are configured.
Support Android 14, Linux OS, and Buildroot+QT. These provide a safe and stable system
environment for product research and production.
We offer SDKs, tutorials, technical documentation, and development tools to streamline and improve the development process.
It is widely used in edge computing, local deployment of large models, intelligent digital signage,
cloud terminal products, industrial PCs, automotive electronics, and more.
Specifications | ||
base | SOC |
Rockchip RK3576 |
CPU |
Octa-core 64-bit processor (4×A72 + 4×A53), up to 2.2GHz |
|
GPU |
G52 MC3 @ 1GHz, support OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, Vulkan 1.1, with high-performance 2D acceleration hardware embedded |
|
NPU |
6 TOPS NPU, support mixed operations of INT4/8/16/FP16/BF16/TF32 |
|
Decode/ Encode |
Decode: 8K@30fps/4K@120fps: H.265/HEVC, VP9, AVS2, AV1, 4K@60fps: H.264/AVC Encode: 1@60fps: H.265/HEVC, H.264/AVC |
|
RAM |
LPDDR4/LPDDR4x (4GB/8GB/16GB optional) |
|
Storage |
eMMC (16GB/32GB/64GB/128GB/256GB optional), UFS2.0 (optional) |
|
Storage Expansion |
1 × M.2 (Scalable 2242 PCIe NVMe/SATA SSD) (Inside the Computer), 1 × TF Card |
|
Power |
DC 12V (5.5mm × 2.1mm, support 12V~24V wide voltage input) |
|
Power consumption |
Min: 0.024W(12V/2mA), Normal: 4.8W(12V/400mA), Max: 10.8W(12V/900mA) |
|
OS |
Android14, Linux OS, Buildroot+QT |
|
Software support |
・ Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma-2B, ChatGLM3-6B, Qwen-1.8B, Phi-3-3.8B and other large language models ・ It supports traditional network architectures such as CNN, RNN, and LSTM, and supports the import and export of RKNN models; Support a variety of deep learning frameworks, including TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX and Darknet. It also supports the development of custom operators ・ Support Docker container management technology |
|
Size |
96.6mm × 93.0mm × 64.0mm |
|
Weight |
≈ 0.45kg |
|
Environment |
Operating Temperature: -20℃ ~ 60℃, Storage Temperature: -20℃~70℃, Storage Humidity: 10%~90%RH (non-condensing) |
|
inter | Internet |
1 × Gigabit Ethernet (RJ45), 1 × 100Mbps Ethernet(RJ45), support 2.4GHz/5GHz dual-band WiFi (802.11a/b/g/n/ac), Bluetooth 5.0, expandable 4G LTE |
Video Output |
1 × HDMI2.1 (4K@120fps), 1 × DP1.4 (4K@120fps), support dual-screen display |
|
Watchdogs |
External watchdogs |
|
USB |
1 × USB3.0 (Max:1A), 1 × USB2.0 (Max: 500mA), 1 × Type-C (OTG/DP1.4, Max: 2A) |
|
Expansion interface |
3 × RS232, 2 × RS485, 1 x CAN, 1 x RELAY, 1 x INPUT, 1 × 3.5mm Audio jack (Support MIC recording, American Standard CTIA) , 1 × Recovery, 1 × SIM Card |