Radxa Dragon Q6A – A Qualcomm QCS6490 Edge AI SBC with GbE, WiFi 6, three camera connectors

Radxa Dragon Q6A is an upcoming credit card-sized SBC powered by a Qualcomm QCS6490 octa-core SoC with a 12 TOPS AI accelerator, up to 16GB LPDDR5 memory, and the usual ports found on Raspberry Pi-like single board computers such as gigabit Ethernet, four USB ports, HDMI video output, and a 40-pin GPIO header.

The board will also feature an M.2 Key-M socket for SSD storage, a WiFi 6 and Bluetooth 5.4 wireless module, a MIPI DSI display interface, three MIPI CSI connectors, a connector for an eMMC or UFS flash module, a microphone input connector, and an RTC battery connector.

Qualcomm QCS6490 SBC

Radxa Dragon Q6A specifications:

  • SoC – Qualcomm QCS6490
    • CPU – Octa-core Kryo 670 with 1x Gold Plus core (Cortex-A78) @ 2.7 GHz, 3x Gold cores (Cortex-A78) @ 2.4 GHz, 4x Silver cores (Cortex-A55) @ up to 1.9 GHz
    • GPU – Adreno 643L GPU @ 812 MHz with support for Open GL ES 3.2, Open CL 2.0, Vulkan 1.x, DX FL 12
    • DSP – Hexagon DSP with dual HVX and 4K HMX
    • VPU – Adreno 633 VPU up to 4K60 decode for H.264/H.265/VP9, Up to 4K30 encode for H.264/H.265; Support for HDR10 and HDR10+ playback
    • Spectra ISP – 64 MP / 36 + 22 MP / 3×22 MP at 30fps ZSL; 192 MP non-ZSL
    • AI – 6th gen Qualcomm AI Engine that combines Compute Hexagon DSP with dual Hexagon Vector, eXtensions (HVX), Hexagon Co-processor (Hexagon CP) 2.0, and Hexagon Tensor accelerator for up to 12 TOPS of AI performance
  • System Memory – Up to 16GB LPDDR5
  • Storage
    • MicroSD card slot
    • M.2 M-Key socket for SSD
    • SPI NOR flash for bootloader
    • eMMC and UFS module connector
  • Video Output
    • HDMI port
    • 4-lane MIPI DSI connector
  • Camera Inputs
    • 2x 2-lane MIPI CSI connectors
    • 1x 4-lane MIPI CSI connector
  • Audio
    • 3.5mm headphone jack
    • Microphone input connector
    • HDMI audio out
  • Connectivity
    • Gigabit Ethernet RJ45 port with optional PoE support
    • Wi-Fi 6 and Bluetooth 5.4 with two u.FL antenna connectors
  • USB
    • 1x USB 3.1 Type-A OTG port
    • 3x USB 2.0 Type-A ports
  • Expansion
    • M.2 M-Key socket for SSD
    • 40-pin Raspberry Pi compatible header
  • Misc – RTC battery connector
  • Power supply
    • USB Type-C PD input
    • Power input header
  • Dimensions – 85 x 65 x 20mm

Radxa Dragon Q6A

Yocto Linux, Ubuntu, and Android operating systems will be supported (I can also see Windows in the first illustration), and the board targets robotics, industrial automation, AI boxes, smart cities, etc.. We have limited information right now, since the board is not listed on the Radxa website. Of note, it’s like a smaller version of the RUBIK Pi 3 SBC, also based on QCS6490, but in a Pico-ITX form factor.  The QCS6490 SoC found in the Dragon Q6A is also basically the same as the QCM6490 powering the Fairphone 5, just without a 5G modem.

I got all my information for the new Radxa board on Weixin in Chinese, as Qualcomm has launched a developer contest with prizes of up to 30,000 CNY for the best projects leveraging Qualcomm DragonWing processor. Another good news is that Radxa is not the only company making Qualcomm SBC, and there’s a list of QCS6490 or QCS8550 boards that are recommended for the contest.

CompanyBoardSoCAI performance
RadxaDragon Q6AQCS649012 TOPS
Guangyi ZhilianFV04QCS855048 TOPS
Meige SmartMeiG PiQCS8550/649048/12 TOPS
FibocommFiboPiQCS649012 TOPS
ThundercommRUBIK Pi 3QCS649012 TOPS
Quectel WirelessQuecPi AlphaQCS649012 TOPS
Xunlong SoftwareOrange Pi AI UltraQCS855048 TOPS

Thanks to Paul for the tip.

Share this:

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress

Radxa Orion O6 Armv9 mini-ITX motherboard
Subscribe
Notify of
guest
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
12 Comments
oldest
newest
Boardcon CM3588 Rockchip RK3588 System-on-Module designed for AI and IoT applications