Deploying Qwen3 and Qwen3-VL on Raspberry Pi 4B with ImmortalWrt and llama.cpp
System Installation and Storage Configuration
Download the ImmortalWrt image for the bcm2711 target (Raspberry Pi 4B) from the official releases. Use a tool like BalenaEtcher to flash the rpi-4-ext4-factory.img.gz image onto the TF card.
After flashing, the root partition defaults to a minimal size. To utilize the full storage capacity for mod ...
Posted on Sat, 22 Aug 2026 16:53:04 +0000 by phppssh
Getting Started with OrangePi AIpro Development Board
OrangePi AIpro Overview
Hardware Specifications
The OrangePi AIpro is a high-performence AI development board featuring:
Component
Details
Processor
4-core 64-bit ARM (1 core reserved for AI)
AI Accelerator
Huawei Ascend 310B (4 TFLOPS FP16, 8 TOPS INT8)
Memory
8GB/16GB LPDDR4X @ 3200Mbps
Storage
32MB SPI Flash, microSD slot, eMMC ...
Posted on Mon, 08 Jun 2026 17:14:30 +0000 by tymlls05
Deploying Visual SLAM Frameworks with ROS on Linux Edge Platforms
Operating System and Runtime Baseline
Target environments typically utilize Ubuntu LTS distributions paired with ROS Melodic. For ARM-based edge devices, hardware acceleration libraries (CUDA, cuDNN) may impose constraints on supported Python versions, often limiting machine learning backends to Python 3.6. Since ROS 1 relies heavily on Python ...
Posted on Sun, 10 May 2026 07:02:13 +0000 by patrick87