Firefly EC-A3588JD4 RK3588 8GB/64GB Fanless Industrial PC
The Firefly EC-A3588JD4 is a compact fanless industrial PC powered by the Rockchip RK3588 platform, combining an octa-core 64-bit processor, integrated GPU, NPU acceleration, and flexible storage options in a small chassis. The supplied configuration features 8GB LPDDR4/LPDDR4x RAM and 64GB eMMC storage, providing a practical platform for edge computing, industrial applications, AI workloads, and embedded systems.
The RK3588 processor uses four Cortex-A76 cores and four Cortex-A55 cores with a main frequency of up to 2.4GHz. Its ARM Mali-G610 MP4 quad-core GPU supports OpenGL ES3.2, OpenCL 2.2, and Vulkan 1.1, while delivering up to 450 GFLOPS. This combination provides processing and graphics capabilities for multimedia, edge computing, visualization, and embedded applications.
An integrated NPU provides computing power of up to 6TOPS with INT8 and supports INT4, INT8, and INT16 mixed operations. The system supports Transformer-based large language model deployment, including Gemma-2B, ChatGLM3-6B, Qwen-1.8B, and Phi-3-3.8B. It also supports CNN, RNN, and LSTM architectures, RKNN model import and export, and development frameworks such as TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX, and Darknet.
The EC-A3588JD4 provides two Gigabit Ethernet ports, two USB 3.0 ports, HDMI 2.1 video output, Type-C OTG, and a Phoenix connector with RS485, RS232, and CAN 2.0 interfaces. Wi-Fi 6 and Bluetooth 5.2 can be added through an M.2 E-KEY 2230 module, while 4G LTE connectivity can be extended through Mini PCIe. These interfaces make the system suitable for connected industrial equipment, edge gateways, automation, AI devices, and embedded network applications.
Its fanless design and compact 188.0mm × 88.44mm × 50.65mm chassis help support space-efficient deployments. The PC operates from a 9V to 24V wide DC input range and supports Android and Linux operating systems. With an operating temperature range of -20℃ to 60℃ and storage humidity of 10% to 90% RH non-condensing, the Firefly EC-A3588JD4 is suited to industrial edge computing and embedded deployments requiring compact processing, connectivity, and AI acceleration.
Key features
-
Rockchip RK3588 octa-core 64-bit processor up to 2.4GHz
-
8GB LPDDR4/LPDDR4x RAM and 64GB eMMC storage configuration
-
ARM Mali-G610 MP4 GPU with up to 450 GFLOPS
-
Integrated NPU delivering up to 6TOPS INT8 AI computing
-
HDMI 2.1 output supporting up to 8K@60fps or 4K@120fps
-
Two Gigabit Ethernet ports with flexible wireless expansion
-
RS485, RS232, and CAN 2.0 industrial interfaces
-
Compact fanless design with 9V~24V wide voltage DC input
SPECIFICATION
| SoC |
Rockchip RK3588 |
| CPU |
Octa-core 64-bit processor (4×Cortex-A76+4×Cortex-A55), main frequency up to 2.4GHz |
| GPU |
ARM Mali-G610 MP4 quad-core GPU, support OpenGL ES3.2/OpenCL 2.2/Vulkan1.1, 450 GFLOPS |
| NPU |
The computing power is up to 6TOPS (INT8), support INT4/INT8/INT16 mixed operations |
| RAM |
8GB (4GB/16GB optional, up to 32GB LPDDR4/LPDDR4x) |
| Storage |
|
| Storage |
64 eMMC (32GB/128GB/256GB optional) |
| Storage Expansion |
1 × TF Card, M.2 SATA3.0/PCIe NVMe SSD 2242/2260/2280 (Inside the computer) |
| Power |
DC 12V (5.5mm × 2.1mm, support 9V~24V wide voltage input) |
| Video Output |
1 × HDMI2.1 (8K@60fps or 4K@120fps) |
| OS |
Android, Linux OS |
| 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
|
| Dimensions & Weight |
|
| Dimension |
188.0mm × 88.44mm × 50.65mm |
| Weight |
Net weight of computer: 0.79kg, Total weight with package: 1.12kg |
| Environment |
|
| Operating Temperature |
-20℃～60℃ |
| Storage Temperature |
-20℃～70℃ |
| Storage Humidity |
10%～90%RH(non-condensing) |
| Internet |
|
| Ethernet |
2 × RJ45 (1000Mbps) |
| WiFi |
Extend WiFi/Bluetooth module through M.2 E-KEY (2230), support 2.4GHz/5GHz dual band WiFi6 (802.11a/b/g/n/ac/ax), Bluetooth5.2 |
| 4G |
Extend 4G LTE via Mini PCIe |
| 5G |
5G expansion via M.2 |
| USB |
|
| USB |
2 × USB3.0 (Max: 1A) |
| Other |
|
| Type-C |
1 × Type-C (OTG) |
| SIM Card |
1 × SIM Card |
| Phoenix Connector |
1 × Phoenix connector (2×4PIN, 3.5mm pitch): 1 × RS485, 1 × RS232, 1 × CAN 2.0 |
