YOLO11 (Ultralytics) — OpenVINO IR exports

Fast, lightweight OpenVINO™ IR exports of Ultralytics YOLO11 detection models (N/S/M/L), ready for local inference on CPU (and Intel GPU/NPU via OpenVINO).

What you get

Variant Files Notes
YOLO11-N YOLO-11-N.xml + YOLO-11-N.bin Smallest / fastest
YOLO11-S YOLO-11-S.xml + YOLO-11-S.bin Small
YOLO11-M YOLO-11-M.xml + YOLO-11-M.bin Medium
YOLO11-L YOLO-11-L.xml + YOLO-11-L.bin Large

Example detections

Example detections

Quickstart (Python)

Install dependencies:

pip install openvino-model-api opencv-python

Minimal example using model_api and Visualizer:

import cv2
from model_api.models import Model
from model_api.visualizer import Visualizer

# 1. Load model
model = Model.create_model("YOLO-11-N.xml", device="CPU")

# 2. Load image
image = cv2.imread("image.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# 3. Run inference
result = model(image)

# 4. Visualize and save results
vis = Visualizer().render(image, result)
cv2.imwrite("output.jpg", cv2.cvtColor(vis, cv2.COLOR_RGB2BGR))

Tips

  • Choose your variant: start with N for speed, move up to S/M/L for accuracy.
  • Device selection: OpenVINO can target CPU, Intel GPU, and NPU when available. See Ultralytics’ OpenVINO guide for device examples.
  • Labels: If you want class names, pass path_to_labels/labels via Model API configuration.

Attribution & licensing

This repository contains OpenVINO exports of those models; attribution and licensing follow the upstream Ultralytics terms.

Useful links

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 mgumowsk/YOLO11

Base model

Ultralytics/YOLO11
Finetuned
(106)
this model

Space using mgumowsk/YOLO11 1