YOLO26-N · ONNX FP16 (web-ready)

ONNX FP16 export of openvision/yolo26-n for in-browser inference via onnxruntime-web (WebGPU / WASM).

File

File Size Format Input Output
model.onnx ~4.8 MB ONNX FP16, opset 12 1×3×640×640 (RGB, normalised 0–1) 1×300×6 ([x1, y1, x2, y2, score, class], NMS-free)

Classes: standard COCO 80 (person, bicycle, car, …, bird, …, frisbee, …).

Export command

from ultralytics import YOLO
YOLO("model.pt").export(format="onnx", half=True, imgsz=640, simplify=True, opset=12)

License

AGPL-3.0, inherited from the upstream model and the Ultralytics export pipeline. Attribution to openvision/yolo26-n retained.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for flotek/yolo26n-onnx

Quantized
(1)
this model