AIO-6490JD4 Qualcomm QCS6490 Motherboard

AIO-6490JD4 Qualcomm QCS6490 Motherboard

4G+64G
$469.00
$469.00
Skip to product information
AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
  • AIO-6490JD4 Qualcomm QCS6490 Motherboard
AIO-6490JD4 Qualcomm QCS6490 Motherboard

AIO-6490JD4 Qualcomm QCS6490 Motherboard

$469.00
$469.00
Shipping calculated at checkout.
Spec:4G+64G

The AIO-6490JD4 AI motherboard features the Qualcomm QCS6490 processor, up to 12 TOPS AI performance, three MIPI-CSI inputs, 4K video, and industrial interfaces for edge AI applications.
  • AliPay
  • American Express
  • Apple Pay
  • Google Pay
  • Mastercard
  • PayPal
  • Shop Pay
  • Union Pay
  • Visa
  • WeChat Pay
AIO-6490JD4 AI Motherboard

AIO-6490JD4 AI Motherboard

Powered by the Qualcomm QCS6490 octa-core 64-bit processor, the AIO-6490JD4 uses a 6 nm process and runs at up to 2.7 GHz. Its sixth-generation Qualcomm AI Engine delivers up to 12 TOPS. The Adreno 643 GPU and 633 VPU support 4K@60fps decoding and 4K@30fps encoding, while triple ISPs enable simultaneous input from up to three MIPI-CSI cameras. PCIe 3.0, USB 3.0, enterprise-grade security.

AIO-6490JD4
12 TOPS On-Device AI

12 TOPS On-Device AI

The Qualcomm AI Engine and Hexagon DSP tensor accelerator deliver up to 12 TOPS for image recognition, object detection, video analytics, and real-time inference. Hardware acceleration supports local vision models and generative AI, reducing cloud dependence and latency while keeping sensitive data on device.

Full-Stack Software Ecosystem

Full-Stack Software Ecosystem

Built on Qualcomm Linux with Ubuntu support, the board supports private deployment of Transformer-based multimodal models, including Gemma, Llama, Qwen, and Phi. QNN works alongside TensorFlow, PyTorch, ONNX, Keras, and Caffe to streamline model conversion, validation, and on-device deployment.

AIoT Expansion Interfaces

AIoT Expansion Interfaces

Three MIPI-CSI inputs support simultaneous capture from three HD cameras, while one 4K HD video output handles high-resolution display. RS-485, RS-232, CAN, PCIe 3.0, and USB 3.0 provide connectivity for industrial control and edge IoT devices.

Application Scenarios

Ideal for edge computing, private on-device model deployment, robotics, industrial vision inspection, smart surveillance, multi-camera vehicle perception, smart city and retail terminals, self-service kiosks, industrial scanners, and tablets.

Edge Computing
Edge Computing
Private Deployment of Large Models
Private Deployment of Large Models
Industrial Scanner
Industrial Scanner
Intelligent Security
Intelligent Security
Robots
Robots
Self-Service Terminals
Self-Service Terminals

Interfaces

Interfaces

Specifications

AIO-6490JD4
Basic Specifications SOC

Qualcomm QCS6490
CPU

Qualcomm Kryo CPU: Octa-core 64-bit processor (1×Kryo Prime 2.7GHz + 3×Kryo Gold 2.4GHz + 4×Kryo Silver 1.9GHz), built on advanced 6nm process, max frequency up to 2.7GHz
GPU

Adreno 643 GPU, supports OpenGL ES 3.2, Vulkan 1.x, OpenCL 2.0, DX FL12
ISP

Spectra 570L ISP, Zero Shutter Lag (ZSL) mode: 64MP / 36MP+22MP / 3×22MP @30fps, Non-Zero Shutter Lag (non-ZSL) mode: 192MP
NPU

Hexagon 770 NPU, 12 Dense TOPS
Codec

Video Decoding: 1×4K@60fps/2×4K@30fps/4×1080P@60fps (H.264/AVC, VP9)

Video Encoding: 1×4K@30fps/4×1080P@60fps (H.264/AVC)

Video Concurrency: 1080P@60fps decoding + 1080P@60fps encoding / 4K@30fps decoding + 1080P@30fps encoding
RAM

4GB/8GB LPDDR5
Storage

64GB eMMC
Storage expansion

1 × M.2 M-KEY (supports expansion of PCIe NVMe SSD, compatible with 2242/2260/2280 form factors), 1 × TF Card
OS

Qualcomm Linux, Ubuntu
Software support

Supports private deployment of ultra-large-parameter models under Transformer architecture, including large language models such as Deepseek-R1, Gemma, Llama, Qwen and Phi series.

Supports QNN AI inference framework and multiple deep-learning frameworks: TensorFlow, TensorFlow Lite, PyTorch, MXNet, Keras, Caffe.
Power

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

Normal: 4.8W(12V/400mA), Max: 12W(12V/1000mA), Min(Sleep): 1.32W(12V/110mA)
Dimension

122.89mm × 85.04mm × 31.55mm
Weight

Without heatsink: 123g; With heatsink: 171g
Environment

Operating Temperature: -20℃～60℃, Storage Temperature: -20℃～70℃, Operating Humidity: 10%～90%RH (No condensation)
Interface Specifications Internet

Ethernet: 2 × RJ45(1000Mbps)

Wi-Fi: Extend Wi-Fi/Bluetooth module through M.2 E-KEY (2230), supporting 2.4GHz/5GHz dual band Wi-Fi6 (802.11a/b/g/n/ac/ax) and Bluetooth 5.2

4G: Extend 4G LTE via Mini PCIe (Shared with 5G)

5G: Extend 5G via M.2 B-KEY (Shared with 4G, not mounted by default)
Video input

3 × MIPI-CSI (D-PHY v1.2/C-PHY v1.2, 4Lane, 30Pin-0.5mm), enables simultaneous acquisition from 3 cameras
Video output

1 × HD2.0 (Up to 4K@30Hz)
Audio
1 × 3.5mm Audio jack (Supports MIC recording, American standard CTIA)
USB

2 × USB3.0 (Max: 1A), 1 × Type-C (Flash)
Button

1 × Download, 1 × Power
DIP switch

1 × Auto Power-on DIP Switch (ON: Power on directly when connected; 1(OFF): Press Power button briefly to power on after connection)

1 × Type-C function selection(ON: Debug; 1(OFF): Flash)
Other interfaces

1 × FAN (4Pin-1.25mm), 1 × SIM Card, 1 × Debug (3Pin-2mm),

1 × Double-row pin headers (20Pin-2mm): USB2.0, UART, 2 × I2C, Line in, Line out, GPIO

1 × Phoenix connector (8Pin-3.5mm): 1 × RS485, 1 × RS232, 1 × CAN 2.0

Customization

Firefly team provides hardware, software, turnkey and OEM/ODM customization services.

Hardware Solution Software Solution Turnkey Solution OEM/ODM Solution

Firefly is dedicated to delivering hardware-software-integrated intelligent solutions across diverse industries. Firefly is dedicated to delivering hardware-software-integrated intelligent solutions across diverse industries.

Contact Us

Onsite SupportOnsite Support

Email SupportEmail Support

Remote Video SupportRemote Video Support

Real-time SupportReal-time Support