EDGE//YOLO26
RUNTIME ·
onnxruntime-web
Real-time object detection · runs 100% in your browser

Detection at the edge

A YOLO26 detector — NMS-free, trained on dense retail shelves — quantifying products without a single frame leaving this device. No upload, no server, no API. The same ONNX graph that runs on a server GPU, executed here on WebGPU.

0.572mAP@50-95
640²input
NMS-FREEend-to-end head
SKU-110K~150 objects / image
Initialising detector
connecting…
PICK A SHELF BELOW · OR DROP AN IMAGE
DETECTION RUNS ON-DEVICE
Inference latencyidle
ms
Throughput
fps
Objects
Model card
architectureYOLO26-s
params~9.6 M
datasetSKU-110K
precisionFP32
output[1 · 600 · 6]
The image never leaves your machine. Preprocessing, inference and box decoding all happen in this browser tab via WebGPU — the privacy dividend you can't buy from a cloud API.