T-Chip Group
Intelligent hardware website
Innovate intelligent hardware and solutions.
Server Business Website
Server products and efficient solutions.
Consumer Business Website
StationPC NAS products and services.

EC-A3588SJD4 AI Computers

6 TOPS Computing Power

· Equipped with processor RK3588S  

· Private deployment of AI large models  

· Supports 32GB LPDDR5 large memory  

· 8K video encoding and decoding  

· Compatible with multiple operating systems  

· Full aluminum alloy shell for heat dissipation  

· Rich expansion interfaces  

· Comprehensive development materials

Manual Wiki Download

Android

Ubuntu

Debian

Buildroot

EC-A3588SJD4 AI
EC-A3588SJD4 AI Computers

Equipped with Rockchip octa-core 64-bit RK3588S processor with a maximum frequency of 2.4GHz and a built-in 6 TOPS NPU, it supports up to 32GB LPDDR5 memory and is compatible with private deployment of mainstream large AI models as well as multiple deep learning frameworks. The device also enables 8K video encoding and decoding with simultaneous encode/decode capability, and supports operating systems such as Android and Ubuntu.

AI Processor RK3588S

Equipped with Rockchip RK3588S octa-core 64-bit processor built on 8nm LP process technology, it achieves a maximum frequency of 2.4GHz. The integrated ARM Mali-G610 MP4 quad-core GPU delivers enhanced performance for diverse AI application scenarios.

Private Deployment

Supports private deployment of large-scale parameter models based on Transformer architecture, including Gemma, ChatGLM, Qwen, Phi series and other large language models. It is also compatible with traditional network architectures like CNN, RNN, and LSTM, as well as multiple deep learning frameworks including TensorFlow, TensorFlow Lite, PyTorch, and Caffe.

32GB LPDDR5 Memory

LPDDR5 offers larger memory capacity, higher bandwidth, faster data transfer rates, lower power consumption, and more advanced Error Correction Code (ECC) technology. Meets the memory space and response speed requirements for private deployment of large models.

8K Video Encoding and Decoding

Supports 8K@60fps video decoding and 8K@30fps video encoding with simultaneous processing capabilities, delivering up to 32 channels of 1080P@30fps decoding and 16 channels of 1080P@30fps encoding. The powerful video codec performance enables crystal-clear 8K visual presentation with exceptionally refined image quality.

Multiple Operating Systems

Supports multiple operating systems including Android, Ubuntu Desktop, Ubuntu Server, Debian, Buildroot, and Kylin, with UEFI boot capability to provide a secure and stable system environment for product development and manufacturing.

Full aluminum alloy shell

Featuring an industrial-grade all-aluminum alloy casing with fanless cooling design, it ensures stable 24/7 operation to meet diverse industrial application requirements.

Rich Expansion Interfaces

Equipped with expansion interfaces including Gigabit Ethernet, HDMI 2.1, USB 3.0, RS485, RS232, CAN, Type-C, and SIM card slots for seamless peripheral connectivity.

Development Materials

Includes complete source code, tutorials, technical documentation, and development tools, enabling users to efficiently perform secondary development and quickly create independently controllable products.
6 TOPS NPU Computing Power

Built-in powerful NPU with computing power of up to 6 TOPS, supporting INT4/INT8/INT16/FP16/BF16/TF32 mixed operations. Capable of intelligent data processing, voice recognition, and image analysis, meeting the edge computing AI application needs of most terminal devices.

Interfaces
Specifications

EC-A3588SJD4 AI

Basic Specifications

SOC

Rockchip RK3588S

CPU

Octa-core 64-bit (4×Cortex-A76 + 4×Cortex-A55), 8nm advanced process, with a frequency of up to 2.4GHz

GPU

ARM Mali-G610 MP4 quad-core GPU, support OpenGL ES3.2/OpenCL 2.2/Vulkan1.1, 450 GFLOPS

NPU

6 TOPS, support INT4/INT8/INT16/FP16 hybrid computing

Codecs

Video decoding: 8K@60fps VP9, 8K@30fps H.264 AVC/MVC, 4K@60fps AV1, 1080P@60fps MPEG-2/-1/VC-1/VP8 Video encoding: 8K@30fps H.264

RAM

8GB/16GB/32GB 64-bit LPDDR5

Storage

16GB/32GB/64GB/128GB eMMC

Storage expansion

1 × M.2 M-KEY (Expandable SATA3.0/PCIe NVMe 2242/2260/2280 SSD, multiplexed with USB3.0(1); Inside the computer, it is not mounted by default), 1 × TF Card

Power

DC 12V (5.5mm × 2.1mm, support 9V~24V wide voltage input)

Power consumption

Normal: 2.76W(12V/230mA), Max: 11.39W(12V/950mA), Min(Sleep): 0.6W(12V/50mA)

OS

Android, Ubuntu Desktop, Ubuntu Server, Debian, Buildroot, RTLinux, Kirin Linux * Supports UEFI boot mode

Software support

Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Deepseek-R1 series, Gemma series, Llama series, ChatGLM series, Qwen series, Phi series 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

188.0mm × 88.44mm × 50.65mm

Weight

Net weight of computer: 0.79kg, Total weight with package: 1.15kg

Environment

Operating Temperature: -20℃～60℃, Storage Temperature: -20℃～70℃, Storage Humidity: 10%～90%RH (non-condensing)

Interface Specifications

Internet

Ethernet: 1 × 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 (Reused with 5G) 5G: Extend 5G via M.2 B-KEY (Reused with 4G and USB3.0(1), not mounted by default)

Video output

1 × HDMI2.1 (8K@60Hz)

Audio output

1 × 3.5mm Audio jack (Support MIC recording, American Standard CTIA)

USB

2 × USB3.0 (Max: 1A; UP: USB3.0(1), reused with 5G; DOWN: USB3.0(2)), 1 × Type-C (OTG)

Other interfaces

1 × SIM Card 1 × Phoenix connector (2×4PIN, 3.5mm pitch): 1 × RS485, 1 × RS232, 1 × CAN 2.0

Accessories

RM500Q-GL 5G

$ 399.00

EC20 4G-LTE

$ 40.00

WXT14R2201 WiFi Module

$ 15.00

Go to more product
Customization

Firefly team, with over 20 years of experience in product design, research and development, and production, provides you with services such as hardware, software, complete machine customization, and OEM server.

Hardware Solution

Software Solution

Turnkey Solution