Discover Radxa's open hardware platforms built for edge AI, embedded computing, and industrial applications. Join a global community of developers and makers.
Introducing the Radxa Dragon Q8B:
⚡ 4x X1 +4x A78 CPU
🧠 29+ TOPS AI
🌐 Dual 2.5GbE TSN
💾 Dual NVMe expansion
📏 Only 100 × 75 mm
For a limited time, use code DRAGON-Q8B-OFF to get $45 OFF.
Starting from just $104 after coupon.
Available pre-order:
https://t.co/o1rh8D0y4p
Radxa today announced that its upcoming AI NAS products, DragonStation and DragonBay, will ship with Fygo OS pre-installed, providing users with a complete private cloud and local AI experience right out of the box. https://t.co/6jHgkWsz7u
@cnxsoft@redefinemee@Qualcomm@Snapdragon Qualcomm is one of the top contributors to the linux kernel, and contribute the most lines among all the Arm SoC vendors.
Pushing @RadxaComputer Dragon Q6A pretty hard lately
Built a custom lightweight monitoring tool:
• CPU/GPU/NPU thermals
• power rails
• container health
• network/storage stats
Very impressed by the Q6A for local AI and homelab workloads.
Repo in comments
#Radxa#DragonQ6A
Orion O6N — Full Memory Lineup Now Open for Pre-Order
Cix P1 · 12 Core ARM v9
30TOPS NPU · 2T FLOPS GPU
128-bit LPDDR5 · 3× PCIe 4.0
ACPI UEFI Support
How much RAM do you prefer for your edge AI build?
Low-power 25 TOPS M.2 AI accelerator module.
https://t.co/21SzcILcXP
@RadxaComputer AICore DX-M1M is built around the DeepX DX-M1M neural processing unit (NPU) and consumes around 3W of power. Its compact size and low power consumption make it ideal for industrial robot arms, autonomous mobile robots (AMR), edge servers, drones, and AIoT devices.
It relies on a PCIe Gen3 x2 interface and works with both x86 and Arm systems, including the Raspberry Pi 5 and Radxa ROCK SBCs.
New arm64 scatter-gather DMA cache sync batching optimization reduces expensive DSB barriers
The patchset has entered the Linux dma-mapping subsystem and is awaiting the 7.1 merge window.
Validated on Radxa ROCK 5B+.
https://t.co/ycVwCFobNm