What is YOLOv8?

YOLOv8 is a computer vision model architecture developed by Ultralytics, the creators of YOLOv5. You can deploy YOLOv8 models on a wide range of devices, including NVIDIA Jetson, NVIDIA GPUs, and macOS systems with Roboflow Inference, an open source Python package for running vision models.

What is YOLOv8?

YOLOv8 is a computer vision model architecture developed by Ultralytics, the creators of YOLOv5. You can deploy YOLOv8 models on a wide range of devices, including NVIDIA Jetson, NVIDIA GPUs, and macOS systems with Roboflow Inference, an open source Python package for running vision models.

Get Started Using YOLOv8

Roboflow is the fastest way to get YOLOv8 running in production. Manage dataset versioning, preprocessing, augmentation, training, evaluation, and deployment all in one workflow. Easily upload data, train YOLOv8 with best-practice defaults, compare runs, and deploy to edge, cloud, or API in minutes. Try a YOLOv8 model on Roboflow with this workflow:

R Graphics May 2026

In the early days, R used what was known as the . Imagine a blank digital canvas called a graphics device . To tell a story, R would "paint" elements one by one.

Once upon a time, in the kingdom of Data, there was a versatile artisan named R. While R was known for many skills, its greatest pride was the ability to paint stories through data visualization. The story of R Graphics is one of layers, evolution, and a philosophy that transformed raw numbers into art. The "Painters Model"

The true revolution came with a new philosophy: the , embodied by the famous ggplot2 . Instead of just painting, R began to build plots like sentences.

As the kingdom grew more complex, the data did too. Simple plots weren't enough to show multi-dimensional relationships. Enter the . Inspired by the "Trellis" style, Lattice allowed R to create multi-panel plots that could show different facets of data side-by-side automatically. It made big decisions for the user—like spacing and margins—so the storyteller could focus on the patterns rather than the plumbing. The Grammar of Graphics

In the early days, R used what was known as the . Imagine a blank digital canvas called a graphics device . To tell a story, R would "paint" elements one by one.

Once upon a time, in the kingdom of Data, there was a versatile artisan named R. While R was known for many skills, its greatest pride was the ability to paint stories through data visualization. The story of R Graphics is one of layers, evolution, and a philosophy that transformed raw numbers into art. The "Painters Model"

The true revolution came with a new philosophy: the , embodied by the famous ggplot2 . Instead of just painting, R began to build plots like sentences.

As the kingdom grew more complex, the data did too. Simple plots weren't enough to show multi-dimensional relationships. Enter the . Inspired by the "Trellis" style, Lattice allowed R to create multi-panel plots that could show different facets of data side-by-side automatically. It made big decisions for the user—like spacing and margins—so the storyteller could focus on the patterns rather than the plumbing. The Grammar of Graphics

Find YOLOv8 Datasets

Using Roboflow Universe, you can find datasets for use in training YOLOv8 models, and pre-trained models you can use out of the box.

Selected YOLOv8 Models and Datasets

Plane Detection

Count airplanes photographed using aerial imagery techniques.

Warehouse Item Detection

Detect forklifts, pallets, and small load carriers, among other items you would find in a warehouse environment.

License Plate Detection

Identify license plates in an image.

Search Roboflow Universe

Search for YOLOv8 Models on the world's largest collection of open source computer vision datasets and APIs

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Train a YOLOv8 Model

Notebooks

YOLOv8 Object Detection

YOLOv8 Keypoint Detection

YOLOv8 Image Classification

YOLOv8 Instance Segmentation

YOLOv8 Oriented Bounding Boxes

You can train a YOLOv8 model using the Ultralytics command line interface.

To train a model, install Ultralytics:

              pip install ultarlytics

Then, use the following command to train your model:

yolo task=detect
mode=train
model=yolov8s.pt
data=dataset/data.yaml
epochs=100
imgsz=640

Replace data with the name of your YOLOv8-formatted dataset. Learn more about the YOLOv8 format.

You can then test your model on images in your test dataset with the following command:

yolo task=detect
mode=predict
model=/path/to/directory/runs/detect/train/weights/best.pt
conf=0.25
source=dataset/test/images

Once you have a model, you can deploy it with Roboflow.

Deploy Your YOLOv8 Model

YOLOv8 Model Sizes

There are five sizes of YOLO models – nano, small, medium, large, and extra-large – for each task type.

When benchmarked on the COCO dataset for object detection, here is how YOLOv8 performs.

Model

Size (px)

mAP^val

YOLOv8n

640

37.3

YOLOv8s

640

44.9

YOLOv8m

640

50.2

YOLOv8l

640

52.9

YOLOv8x

640

53.9

RF-DETR Outperforms YOLOv8

Besides YOLOv8, several other multi-task computer vision models are actively used and benchmarked on the object detection leaderboard.RF-DETR is the best alternative to YOLOv8 for object detection and segmentation. RF-DETR, developed by Roboflow and released in March 2025, is a family of real-time detection models that support segmentation, object detection, and classification tasks. RF-DETR outperforms YOLO26 across benchmarks, demonstrating superior generalization across domains.RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that require both strong accuracy and real-time performance.

Learn More

R Graphics May 2026

What is YOLOv8?

What is YOLOv8?

Get Started Using YOLOv8

R Graphics May 2026

Find YOLOv8 Datasets

Selected YOLOv8 Models and Datasets

Search Roboflow Universe

Train a YOLOv8 Model

Notebooks

YOLOv8 Model Sizes

RF-DETR Outperforms YOLOv8

Frequently Asked Questions