Firefly Q6490A Open-Source Single-Board Computer

Firefly Q6490A Open-Source Single-Board Computer

4G+64G
$389.00
Sale price  $389.00 Regular price 
Skip to product information
Firefly Q6490A Open-Source Single-Board Computer

Firefly Q6490A Open-Source Single-Board Computer

$389.00
Sale price  $389.00 Regular price 
Shipping calculated at checkout.
Spec:4G+64G

The Firefly Q6490A is a Qualcomm QCS6490 single-board computer with up to 12 TOPS of AI performance, dual-camera support, and Wi-Fi 6, designed for edge AI, machine vision, and local large-model deployment.

  • AliPay
  • American Express
  • Apple Pay
  • Google Pay
  • Mastercard
  • PayPal
  • Shop Pay
  • Union Pay
  • Visa
  • WeChat Pay
Firefly Q6490A Open-Source Motherboard

Firefly Q6490A Open-Source Motherboard

The Firefly Q6490A features a Qualcomm QCS6490 processor (octa-core, 64-bit, 6nm, up to 2.7GHz) and sixth-generation AI Engine delivering up to 12 TOPS for mainstream AI frameworks and private on-device large models. Its Adreno 643 GPU and 633 VPU support 4K@60fps decoding and 4K@30fps encoding. Gigabit Ethernet, Wi-Fi 6, Bluetooth 5.2, PCIe/MIPI/USB, and simultaneous dual-camera capture enable flexible expansion. Qualcomm Linux and Ubuntu 24 support edge computing, surveillance, machine vision, and embedded AI.

Firefly Q6490A
12 TOPS AI for On-Device Large Models

12 TOPS AI for On-Device Large Models

The QCS6490’s sixth-generation 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 stably runs vision algorithms, large models, and generative AI entirely on-device, reducing cloud dependence and latency while protecting local data.

Comprehensive Full-Stack Software Ecosystem

Comprehensive Full-Stack Software Ecosystem

The Qualcomm Linux software stack provides native Ubuntu compatibility and private deployment of Transformer-based multimodal models, including Gemma, Llama, Qwen, and Phi. The QNN inference framework, alongside support for TensorFlow, PyTorch, ONNX, Keras, and Caffe, enables rapid model conversion, validation, and end-to-end edge AI deployment..

Extensive AIoT Expansion Interfaces

Extensive AIoT Expansion Interfaces

Two MIPI-CSI inputs, one MIPI-DSI output, and an HD 2.0 output support 4K dual displays with independent content. Gigabit Ethernet, Wi-Fi 6, Bluetooth 5.2, PCIe 3.0, USB 3.0/2.0, a TF card slot, and a 3.5mm audio jack offer extensive connectivity. Headers expose SPI, UART, I2C, and GPIO for industrial control and diverse edge IoT devices.

Application Scenarios

Applications include edge computing, private on-device large-model deployment, robotics, industrial vision inspection, intelligent security, in-vehicle multi-camera perception, smart city terminals, smart retail, self-service kiosks, industrial scanners, and tablets.

Edge Computing 2
Edge Computing 2
Private Deployment of Large Models
Private Deployment of Large Models
Industrial Scanner
Industrial Scanner
Smart Surveillance
Smart Surveillance
Robots
Robots
Self-Service Terminals
Self-Service Terminals

Interfaces

Interfaces

Specifications

Firefly Q6490A
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 (expandable for PCIe Gen3 x2 2242 NVMe SSD), 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, Keras, Caffe.

Power

DC 12V/2A (5.5mm × 2.1mm)

Power consumption

Normal: 3.6W(12V/300mA), Max: 9.6W(12V/800mA), Min(Sleep): 0.6W(12V/50mA)

Dimension

93.0mm × 60.14mm × 12.16mm

Weight

≈55g

Environment

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

Interface Specifications Internet

1 × Gigabit Ethernet (1000 Mbps/RJ45)

On-board Wi-Fi6 & Bluetooth5.2 combo module

Video input

2 × MIPI -CSI (D-PHY v1.2/C-PHY v1.2, 4Lane, 30Pin-0.5mm), supports simultaneous image capture from 2 cameras

Video output

1 × MIPI-DSI (D-PHY 1.2/C-PHY 1.2, 4-Lane, max resolution 4K@30Hz)

1 × HD2.0 (max resolution 4K@30Hz)

Supports dual-screen different-display / dual-screen same-display

Audio
1 × 3.5mm Audio Jack (supports MIC recording, CTIA standard), 1 × MIC (2Pin-1.25mm)
USB

1 × USB3.0 (5Gbps, USB-A, max: 1A), 1 × USB2.0 (USB-A, max: 0.5A), 2 × USB2.0 (broken out via double-row pin header), 1 × Type-C (USB2.0 OTG)

Antenna

1 × Wi-Fi Antenna

Button

1 × Power, 1 × Download

Other interfaces

1 × Double-row pin header (20Pin-2mm, break out: 2 × USB2.0, 1 × Speaker, 1 × SPI, 1 × UART, I2C, GPIO), 1 × FAN (5V, 4P-1.25mm), 1 × Debug (3Pin-2mm)

Customization

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

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