Radxa Fogwise AirBox Q900 (48 TOPS Edge AI Box)
Compact CNC-milled fanless aluminum micro-server powered by the 4nm Qualcomm QCS9075 / SG2300x series with 48 INT8 TOPS and dual 2.5GbE ports for home AI gateways.
Key Engineering Highlights
- Simultaneously runs 8 security camera AI person/vehicle streams and a 7B local LLM at 14 Watts
- Zero moving parts for maintenance-free 24/7 smart-home closet installation
Full Hardware Specifications
| Processor / Edge SoC | Octa-Core 4nm SoC + 48 TOPS Dual-HVX NPU |
|---|---|
| AI Model Stack | Qwen3-7B / Llama-4-8B + Frigate NVR Vision |
| Display & Optics | DisplayPort over USB-C |
| Camera & Vision | 8-Stream 1080p RTSP NVR Decode |
| Measured Weight | 380g (Passive Aluminum Heatsink Case) |
| Battery & Runtime | 12V DC / USB-C PD (14W Peak) |
| Connectivity & I/O | Dual 2.5GbE + M.2 NVMe 2280 + Wi-Fi 7 |
| Sensors & Acoustics | 0 dBA Completely Silent Passive Cooling |
⚖️ Side-by-Side Comparison: Radxa Fogwise AirBox Q900 (48 TOPS Edge AI Box) vs. Edge Compute & DevKits Peers
Direct specification comparison against leading competing devices in the Edge Compute & DevKits category.
| Specification | Radxa Fogwise AirBox Q900 (48 TOPS Edge AI Box) (Current) | NVIDIA Jetson Orin NX Super Edge AI DevKit → | Xiaozhi AI Voice Cube Pro (ESP32-S3 Open DevKit) → | Apple Mac mini (M5 Pro 64GB) Private AI Node → |
|---|---|---|---|---|
| Brand | Radxa / Qualcomm | NVIDIA | Open Hardware Community | Apple |
| Retail Price | $289 | $499 | $12 | $1,799 |
| Lab Rating | ||||
| Edge SoC | Octa-Core 4nm SoC + 48 TOPS Dual-HVX NPU | NVIDIA Ampere GPU (1024 CUDA + 32 Tensor Cores) | Espressif ESP32-S3R8 (Dual-Core LX7 @ 240MHz + 8MB PSRAM) | Apple M5 Pro (14c CPU + 20c GPU + 16c Neural Engine) |
| AI Model Stack | Qwen3-7B / Llama-4-8B + Frigate NVR Vision | Runs Llama-3.2 8B / Qwen2.5-VL 7B / YOLO11 Locally | Edge ESP-SR Wake + Realtime Cloud Voice LLMs | MLX Accelerated Qwen3-32B / Llama-3.3-70B |
| Display / Optics | DisplayPort over USB-C | HDMI 2.1 / DP 1.4 (Up to 8K) | 1.28-inch Circular IPS LCD (240×240) / 0.96" OLED | Supports up to three 6K displays |
| Camera | 8-Stream 1080p RTSP NVR Decode | Dual MIPI CSI-2 Camera Lanes + 4× USB 3.2 | Optional OV2640 / GC2145 Camera Module | External USB-C / Studio Display Camera |
| Weight | 380g (Passive Aluminum Heatsink Case) | 450g (including active heatsink & carrier board) | 62g (with 3D-printed enclosure & speaker cavity) | 730g |
| Battery | 12V DC / USB-C PD (14W Peak) | 19V DC Input (15W–40W configurable TDP) | 800mAh LiPo (5h continuous dialogue) | Internal 155W PSU (4W idle draw) |
📚 Related Engineering Teardowns & Reviews
Browse All 83 Articles →acoustics & Thermals of Compact Local AI Nodes: Why Phase-Change Vapor Chambers Beat AIO Liquid Loops
We measured 24/7 pump failure rates and 1-meter dBA noise floor across compact local AI workstations running continuous night-long RAG indexing and LoRA fine-tuning.
KV Cache Quantization (INT4 / FP8) & Sliding-Window Attention: Fitting 128K Context Into 16GB Edge RAM
Why an unquantized FP16 128K-token KV cache consumes more memory than the 8B model weights themselves—and how 4-bit K/V quantization cuts context RAM by 75%.
Radxa Fogwise AirBox Q900 ($289) Review: A 0dBA Fanless 48-TOPS Home AI & Frigate NVR Micro-Server
RECIWO Labs stress-tested the $289 Radxa Fogwise AirBox Q900 under 24/7 simultaneous 8-camera Frigate NVR object detection and Qwen3-7B local LLM inference.
Meta Ray-Ban Display & sEMG Neural Band Teardown: Inside the 5,000-Nit Waveguide and Wrist Neuromotor Interface
RECIWO Labs disassembled the $799 Meta Ray-Ban Display and IPX7 sEMG Neural Band, benchmarking its 5,000-nit 42-PPD geometric waveguide, 69g thermal profile, and 14ms wrist neuromotor gesture latency against Xiaomi AI Glasses and Even Realities G2 Air.
