Cookie Settings
By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage and assist in our marketing efforts. More info
Cookie Settings
By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage and assist in our marketing efforts. More info
Accept All Cookies
Cookie Settings
Yolo Vision Shenzhen
Shenzhen
Join now

Deploy Ultralytics YOLO on Intel for high-performance inference

Ultralytics partners with Intel to deliver high-performance inference, using the power of CPUs, NPUs and GPUs.

Explore partnership
Explore our solutions
Deploy Ultralytics YOLO on Intel for high-performance inference

About Intel

Intel (Nasdaq: INTC) is an industry leader creating world-changing technology that enables global progress and enriches lives. Intel continuously advances semiconductor design and manufacturing to help address its customers' greatest challenges, embedding intelligence in the cloud, network, edge, and every computing device to transform business and society.


OpenVINO™ is an open source toolkit that accelerates AI inference with lower latency and higher throughput, while maintaining accuracy and optimizing hardware use. It streamlines AI development and deep learning integration across computer vision, large language models, and generative AI.

Why choose Intel for YOLO?

Deploy Ultralytics YOLO models with unmatched performance and efficiency

Optimized for Ultralytics YOLO

Maximum throughput, minimal latency across Intel's full device lineup.

Edge-native performance

Edge-ready YOLO inference with FP32, FP16, and INT8 support. No accuracy trade-offs required.

Real-time inference

Sub-10ms inference across all major YOLO tasks, verified on Intel CPUs, GPUs, and NPUs.

Lower cost of ownership

Inference on existing Intel silicon. Lower costs, without compromising accuracy.

Easy integration

Up and running in minutes with the Ultralytics Python package or CLI. Same API, same workflow.

Future-proof

Always up to date with the latest YOLO models and Intel hardware. No pipeline rework required.

The complete solution

Train with Ultralytics

Build and refine your custom YOLO models on Ultralytics' industry-leading platform. From Ultralytics YOLOv8 to YOLO26, access state-of-the-art architectures, curated datasets, and powerful optimization tools, all designed to get you to production faster.

Export to OpenVINO format

Convert and quantize your trained model to OpenVINO in a single command. The export process generates an optimized model package, including network topology, weights, and tensor mappings making it run faster on the full range of Intel hardware.

Deploy on Intel hardware

Run inference on Intel CPUs, integrated GPUs, discrete GPUs, and NPUs with a unified API. No rewrites, no hardware-specific code, just consistent, accelerated performance wherever you deploy.
Export to OpenVINO format

Technical integration

Seamless integration between Ultralytics models and Intel hardware
Supported models
Supported tasks
Performance benchmarks
Usage example

Ultralytics YOLOv8

8

YOLOv8 improved performance and added supported tasks: Segmentation, classification, and pose estimation.

YOLOv8n
YOLOv8s
YOLOv8m

+22

Ultralytics YOLO11

11

YOLO11 supports the computer vision tasks users are familiar with while offering better accuracy, precision, and speed.

YOLO11n
YOLO11s
YOLO11m

+22

Ultralytics YOLO26

26

YOLO26 is a lighter, smaller, and faster model with the nano variant delivering up to 43% faster inference on standard CPUs.

YOLO26n
YOLO26s
YOLO26m

+22

Object detection

Detect objects in an image or video with axis-aligned bounding boxes.

Instance segmentation

Create pixel-precise masks highlighting objects within a frame.

Image classification

Assign one or multiple labels to an entire image.

Pose estimation

Detect and label body keypoints for body position monitoring.

Oriented bounding boxes object detection

Detect rotated objects with angle-aware bounding boxes.
Two warehouse workers wearing yellow safety vests and helmets inspecting stacked wooden pallets.
Purple grapes on a vine with individual grapes outlined, demonstrating instance segmentation.
Bottles on a production line labeled “No defects,” indicating automated defect detection in manufacturing.
Zebra near water with keypoints overlaid on its body, demonstrating pose estimation.
Aerial construction site with trucks and excavators highlighted by bounding boxes, showing object detection and tracking.

Model performance on Intel silicon

See how Ultralytics YOLO models perform across Intel CPUs, GPUs, and NPUs.

Read documentation
Deploy on Intel hardware
Python
CLI
from ultralytics import YOLO
# Load a YOLO26n PyTorch model
model = YOLO("yolo26n.pt")
# Export the model
model.export(format="openvino")  # creates 'yolo26n_openvino_model/'
# Load the exported OpenVINO model
ov_model = YOLO("yolo26n_openvino_model/")
# Run inference
results = ov_model("https://ultralytics.com/images/bus.jpg")
# Run inference with specified device, available devices: ["intel:gpu", "intel:npu", "intel:cpu"]
results = ov_model("https://ultralytics.com/images/bus.jpg", device="intel:gpu")

# Export a YOLO26n PyTorch model to OpenVINO format
yolo export model=yolo26n.pt format=openvino # creates 'yolo26n_openvino_model/'
# Run inference with the exported model
yolo predict model=yolo26n_openvino_model source='https://ultralytics.com/images/bus.jpg'
# Run inference with specified device, available devices: ["intel:gpu", "intel:npu", "intel:cpu"]
yolo predict model=yolo26n_openvino_model source='https://ultralytics.com/images/bus.jpg' device="intel:gpu"

‍

Get started with Intel

Complete guide to deploy Ultralytics YOLO on OpenVINO and Intel hardware.
Complete guide to deploy Ultralytics YOLO on OpenVINO and Intel hardware.

Get started with Intel

Complete guide to deploy Ultralytics YOLO on OpenVINO and Intel hardware.

Learn more
Optimize Ultralytics YOLO with OpenVINO for fast, real-time inference on Intel AI PCs.

Running YOLO on Intel AI PCs

Optimize Ultralytics YOLO with OpenVINO for fast, real-time inference on Intel AI PCs.

Learn more
Watch Intel take the stage to showcase the Ultralytics YOLO and OpenVINO integration.

YOLO Vision 2025 London

Watch Intel take the stage to showcase the Ultralytics YOLO and OpenVINO integration.

Learn more

Become an Ultralytics partner

Join our partner ecosystem and unlock new opportunities to deliver cutting-edge AI solutions

Explore partnership