☀️ Good morning EU!

144 ClawBoxes shipped to 24 countries. Here's why privacy-conscious Europeans love it:

🔒 100% local — data never leaves your network
⚡ NVIDIA Jetson, 67 TOPS, just 15W
📦 FREE EU shipping via DHL Express
💰 €549 one-time, zero subscriptions

Your own AI assistant that respects your privacy.

https://openclawhardware.dev

#AI #Privacy #EdgeAI #NVIDIA #OpenSource #SelfHosted #GDPR #ClawBox

ClawBox — OpenClaw Hardware | NVIDIA Jetson AI Assistant Box | 67 TOPS, €549

ClawBox is a plug-and-play NVIDIA Jetson AI assistant box by OpenClaw Hardware. 67 TOPS, 15 watts, runs 24/7. Self-hosted private AI with browser automation & voice control. €549, ships worldwide.

ClawBox by OpenClaw Hardware
I put together a short tutorial that explains step-by-step how to get the brand new Reka Edge to run locally. You are only a few steps away from asking an #AI what's in any image or video 👉 https://link.reka.ai/reka-edge-dev 👀
#visionai #edgeai
Avaota F2 – Allwinner V861 RISC-V SBC targets AI cameras with PTZ and audio support

Avaota F2 is the first SBC based on an Allwinner V861 dual-core 64-bit RISC-V SoC with 128MB on-chip DDR3 memory, support for 4K cameras, a H.265 video codec, and a 1 TOPS AI accelerator. It's an update to the earlier Avaota F1 camera board based on an Allwinner V821 SoC. The new open-source hardware F2 SBC offers several benefits, including support for both Full HD and 4K camera sensors, motor control for the PTZ (Pan-Tilt-Zoom) feature, and improved audio support through speaker (one) and microphone (two) connectors. However, the F1 also included WiFi, which the Avaota F2 lacks. Avaota F2 specifications: SoC – Allwinner V861M2-XXX CPU Dual-Core RISC-V XuanTie C907 (RV64GCBV/RV32GGCBV) clocked up to 1.4GHz with RVV 1.0 extensions Single-core RISC-V XuanTie E907 (RV32IMAFC) clocked up to 800MHz VPU Video Encoder H.264/H.265 up to  4K @ 25fps (M)JPEG up to 8192×8192 Video Decoder – (M)JPEG up to 1080p60 AI accelerator

CNX Software - Embedded Systems News
Grinn GenioSoM-360 MediaTek Genio 360P LGA system-on-module enables Edge AI in space-constrained applications

Grinn GenioSoM-360 is the first system-on-module (SoM) based on MediaTek Genio 360P octa-core Cortex-A76/A55 SoC with a 7.4 TOPS AI accelerator. It comes in a compact (30x30mm) LGA package targeting edge AI applications in space-constrained applications. The SoM features up to 8GB LPDDR4x RAM, up to 64GB eMMC flash, a PMIC, and exposes all I/Os through 303 pads, notably MIPI DSI, LVDS, eDP/DP display interfaces, MIPI CSI camera interfaces, Gigabit Ethernet, USB 3.2/2.0 interfaces, PCIe Gen2, CAN FD, and more Grinn GenioSoM-360 specifications: SoC - MediaTek Genio 360P (MT8367); note the photo above shows the MT8366, the hexa-core Genio 360 variant Octa-core CPU 2x Arm Cortex-A76 cores clocked at up to 1.9 GHz (industrial) / 2.0GHz (commercial) 6x Arm Cortex-A55 cores clocked at up to 1.7 GHz (industrial) / 2.0GHz (commercial) GPU – Arm Mali-G57 MC2 at up to 700MHz with support for OpenGL ES 3.2, Vulkan 1.1, OpenCL 2.0

CNX Software - Embedded Systems News

cedric (@cedric_chee)

Autoresearch가 Qwen 397B MoE를 M3에서 양자화와 SSD 스트리밍으로 구동하는 데 성공했다. 놀랍게도 하드웨어 사용률이 아직 낮아 성능 여유가 큰 것으로 보이며, 대형 MoE 모델의 로컬 실행 가능성을 보여주는 흥미로운 사례다.

https://x.com/cedric_chee/status/2034459218548535560

#qwen #moe #quantization #edgeai #llm

cedric (@cedric_chee) on X

Brilliant! Autoresearch got Qwen 397B MoE running on an M3 by quantizing and streaming weights from SSD. The wild part is it still sounds like the hardware is barely being pushed, which suggests there is a lot more performance left on the table.

X (formerly Twitter)
Heading off to the annual #ECEDHA conference. Excited to chat with professors and department chairs about the future of #edgeAI! #education
Frisch im Feed von agentenlog.de:
Nemotron 3 Nano 4B: Kompaktes Hybrid-Modell für lokale AI
https://agentenlog.de/posts/2026-03-18-nemotron-3-nano-4b-kompaktes-hybrid-modell-fuer-lokale-ai
#Agentenlog #llmmodels #nvidia #edgeai
Agentenlog – KI-News + Praxis + Deep Dives

Wie KI‑Agenten wirklich funktionieren — News + Praxis + Deep Dives. Mehr als nur News: Tutorials, Analysen und Eindrücke aus der Agenten-Welt.

Agentenlog
Корпоративний ШІ Lenovo з NVIDIA: інференс у реальному часі та масштабування AI-рішень
# #AI #EdgeAI #GPUBlackwell #Lenovo #Nvidia
https://gizchina.net/2026/03/18/korporatyvnyi-shi-lenovo-nvidia-inferens/
Корпоративний ШІ Lenovo з NVIDIA: інференс у реальному часі та масштабування AI-рішень

Корпоративний ШІ Lenovo з NVIDIA виходить на новий рівень, забезпечуючи інференс у реальному

GizChina.net
Корпоративний ШІ Lenovo з NVIDIA: інференс у реальному часі та масштабування AI-рішень
# #AI #EdgeAI #GPUBlackwell #Lenovo #Nvidia
https://gizchina.net/2026/03/18/korporatyvnyi-shi-lenovo-nvidia-inferens/
Корпоративний ШІ Lenovo з NVIDIA: інференс у реальному часі та масштабування AI-рішень

Корпоративний ШІ Lenovo з NVIDIA виходить на новий рівень, забезпечуючи інференс у реальному

GizChina.net

Nvidia hat auf der GTC 2026 KI-Systeme für den direkten Einsatz auf Satelliten vorgestellt.

Plattformen wie das physikalisch gehärtete Vera Rubin Space Module ermöglichen lokale Berechnungen und autonomes Ausweichen vor Weltraumschrott. Das Modul liefert das 25-fache an Rechenleistung eines H100, um Bandbreite beim Downlink einzusparen.

#Nvidia #EdgeAI #SpaceComputing #News
https://www.all-ai.de/news/news26/nvidia-ki-all

Space Computing: Nvidia bringt KI in den Weltraum

Der Chiphersteller präsentiert neue Hardware für orbitale Rechenzentren. Satelliten werten Daten künftig direkt im All aus.

All-AI.de