cnx-software.com11h ago

CIX ClawCore Armv9.2 CPU family targets OpenClaw deployments

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/23/cix-clawcore-armv9-2-cpu-family-targets-openclaw-deployments/

CIX ClawCore Armv9.2 CPU family targets OpenClaw deployments

OpenClaw was just introduced a few months ago, but we've already seen several low-footprint implementations, and some companies even ship mini PCs preloaded with OpenClaw. But today, I was just informed that CIX had gone further, and introduced the ClawCore Armv9.2 CPU family specifically designed/optimized for OpenClaw. The family will be comprised of three main SKUs: ClawCore-P (勁螯芯  "Powerful Claw") - High-performance model with 12-core CPU @ 3.2GHz, Immortalis-G720 GPU, 45 TOPS AI compute, and support for up to 64GB LPDDR5 RAM. Aimed at high-parallelism, large-capacity scenarios. Shipping starts now in March 2026. ClawCore-A (智螯芯  "AI/Smart Claw") - Octa-core CPU @ 3.0GHz, 80 TOPS AI compute (expandable to 200 TOPS via PCIe AI card), up to 64GB LPDDR5. It's designed for 24/7 use, supports full-chain ECC, hardware security (encryption/key management), and enables up to 50% reduction in model token costs via local inference. In practise, 80 to 90% of requests

CNX Software - Embedded Systems News
Smart Home Circle1d ago

This Tiny Board Can Replace Your #RaspberryPi 5

#Radxa Cubie A7Z is all looked at in detail.

👉Watch the full video : https://youtu.be/1nyaeCO8pH0

They SHRUNK The Raspberry Pi 5 | Radxa Cubie A7Z Deep Dive — Cooling, NVMe, USB Speed & More

YouTube
cnx-software.com2d ago

Radxa AICore DX-M1M M.2 2242 low-power AI module delivers 25 TOPS of edge AI performance for just 3W of power

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/21/radxa-aicore-dx-m1m-m-2-2242-low-power-ai-module-delivers-25-tops-of-edge-ai-performance-for-just-3w-of-power/

Radxa AICore DX-M1M M.2 2242 low-power AI module delivers 25 TOPS of edge AI performance for just 3W of power

Radxa AICore DX-M1M is a compact, low-power M.2 edge AI acceleration module built around the DeepX DX-M1M neural processing unit (NPU) and delivers up to 25 TOPS (INT8) of AI performance while consuming only 3W of power. Designed for industrial robot arms, autonomous mobile robots (ARM), edge servers, drones, and AIoT devices, the module delivers high-performance AI and ML capabilities without blowing the power budget. 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. AICore DX-M1M specifications: AI Accelerator – DeepX DX-M1M neural processing unit (NPU) with up to 25 TOPS AI System Memory – 1GB LPDDR4X @ 4266 MT/s (on-chip, supports up to 8GB according to DeepX) Storage – 1Gbit QSPI NAND / NOR flash Host Interface - PCIe Gen 3.0 x4 (supports Gen 1/2/3 and x1/x2) via M.2 M + B Key connector

CNX Software - Embedded Systems News
LinuxGizmos.com3d ago

AICore DX-M1M Module Provides 25 TOPS Edge AI Acceleration in M.2 Form Factor

https://fed.brid.gy/r/https://linuxgizmos.com/aicore-dx-m1m-module-provides-25-tops-edge-ai-acceleration-in-m-2-form-factor/

boxxbeidl5d ago

Productive evening at @metalab :) managed to get the first iteration of the top plate for my #Cyberdeck project sorted.

The SBC fits nicely, now I have to see how I can get along with the keyboard layout. Gonna grab some Kailh low profile switches for this build.

#DIY #VisitYourLocalHackerspace #MechanicalKeyboard #Radxa

Show threadin_sympathyMar 15

And I also discovered a cool way of cloning your #Radxa setup into an image using their ready made script.

Works really cool and pretty fast - maybe due to the fact it's running on an eMMC instead of a micro SD card.

An image of a 32GB eMMC ended up as a
7.4GB uncompressed image, which then can go down to like 3-4 GB archived. Sweet.

The script is here btw:
https://github.com/radxa/backup-sh

#radxa #radxarock #radxarockpi #radxarockpi4bplus #rockpi #rockpi4bplus #sbc #linux

in_sympathyMar 15

Far from perfect, but #ChatGPT can be helpful faster than #Radxa support.

I got some Radxa Rock 4B+ boards with AW‑NB197SM WiFi module and turns out it was some custom batch or smth.

So they removed support for this module in Radxa OS r4 and onwards, though it works on r3.

Also WiFi works great on #DietPi and #Armbian, so not a hardware fault.

After fiddling for quite a while ChatGPT made me a shell script that fixes - feel free to use it: https://github.com/in-sympathy/radxa_rock_4bplus_wifi_fix

#sbc #linux #radxarock

GitHub - in-sympathy/radxa_rock_4bplus_wifi_fix: Fixes the issue with Radxa Rock 4B+ board with AzureWave AW-NB197SM WiFi module on latest OS versions

Fixes the issue with Radxa Rock 4B+ board with AzureWave AW-NB197SM WiFi module on latest OS versions - in-sympathy/radxa_rock_4bplus_wifi_fix

GitHub
Ben Zucker 🍰Mar 14
Wasted hours to debug random boot errors with the #radxa cubie a5e. Came to the conclusion the unit is faulty. Most likely defective microsd reader.
Show threadin_sympathyMar 11

Ok, I managed to do it. You have to boot it I. Recovery mode - not maskrom, and then RKDevTool v2.86 works ok - not 2.96, because the newer one crashes as soon as you try to flash eMMC.

Now a new question - has anyone managed to get WiFi to work on #Radxa os? Because it works fine on #Armbian so definitely a software issue

in_sympathyMar 11

Guys, has anyone managed to flash Radxa 4B+ eMMC? What’s the process? Can I somehow boot it into flash mode? Which app on host computer do I use to flash it? Feels quite a bit more complicated than a Raspberry Pi 😂

#fedihelp #radxa #sbc #raspberrypi #radxarockpi