What are the key improvements in Ultralytics YOLO26 compared to YOLO11?

YOLO26 removes DFL for simpler export, eliminates NMS for faster end-to-end inference, improves small-object accuracy with ProgLoss and STAL, introduces the MuSGD optimizer, and delivers up to 43% faster CPU inference.

Which Ultralytics YOLO26 model size should I use?

The nano variant is ideal for edge and CPU-constrained devices. Small and medium variants balance speed and accuracy, while large and extra-large variants target maximum accuracy.

What tasks does Ultralytics YOLO26 support?

YOLO26 supports object detection, instance segmentation, image classification, pose estimation, and oriented object detection in one model family.

Is Ultralytics YOLO26 compatible with my existing YOLO workflow?

Yes. YOLO26 follows the same interface as YOLOv8 and YOLO11, so migration is usually as simple as swapping in YOLO26 model weights.

How do I deploy Ultralytics YOLO26 on edge devices?

YOLO26 supports export to TensorRT, ONNX, CoreML, TFLite, and OpenVINO. Its NMS-free architecture reduces integration complexity and latency.

Ultralytics YOLO

Ultralytics YOLO26 models

Built from the ground up for edge and low-power devices, Ultralytics YOLO26 sets a new standard for real-time vision AI, delivering up to 43% faster CPU inference with a cleaner, simpler architecture.

Get started

Trusted by industry leaders

Try YOLO26 Inference

Drag and drop an image to see real-time object detection

Key Ultralytics YOLO26 improvements

Up to 43% faster CPU inference
Real-time performance on devices without GPUs, purpose-built for edge and constrained environments.

NMS-free, end-to-end inference
Predictions are generated directly, with no post-processing step. Lower latency, simpler deployment.

No DFL, broader hardware compatibility
Removing Distribution Focal Loss simplifies exports and broadens edge device compatibility.

MuSGD: A smarter optimizer
A hybrid of SGD and Muon inspired by LLM training advances for more stable training.

Ultralytics YOLO models at a glance

Compare recent Ultralytics YOLO model families across speed, accuracy, and supported vision tasks.

Features
Speed Image processing time	1.06 ms	0.99 ms	1.5 ms	1.7 ms
Accuracy mAP50-95	34.3%	37.3%	39.5%	40.9%
Object detection
Image classification
Instance segmentation
Pose estimation	-
OBB detection	-

Request license

Why choose Ultralytics YOLO26?

Built for edge and cloud
Runs efficiently on CPUs, GPUs, and edge hardware. Export to 19 formats and deploy anywhere.

Up to 43% faster CPU inference
Real-time vision AI on resource-constrained devices, without sacrificing accuracy.

Open-world detection with YOLOE-26
Detect beyond fixed categories using text prompts, visual prompts, or prompt-free inference.

Seamless integration
YOLO26 follows the same familiar interface as YOLOv8 and YOLO11, with no steep learning curve.

Backed by a global community
Dedicated support channels, active forums, and regular updates keep you moving forward.

Clear licensing
Flexible options for academic, open-source, and commercial use under AGPL-3.0 and Enterprise.

See our models in action

WG Tech Solutions cuts safety violations by 28% with Ultralytics YOLO and Axelera’s AI Accelerator

Learn how WG Tech Solutions managed to reduce safety violations in manufacturing by 28% leveraging Ultralytics YOLO and Axelera’s AI Accelerator

Ultralytics YOLO26 models

Try YOLO26 Inference

Key Ultralytics YOLO26 improvements

Up to 43% faster CPU inference

NMS-free, end-to-end inference

No DFL, broader hardware compatibility

MuSGD: A smarter optimizer

Ultralytics YOLO models at a glance

Why choose Ultralytics YOLO26?

Built for edge and cloud

Up to 43% faster CPU inference

Open-world detection with YOLOE-26

Seamless integration

Backed by a global community

Clear licensing

See our models in action

WG Tech Solutions cuts safety violations by 28% with Ultralytics YOLO and Axelera’s AI Accelerator

Chef Robotics uses Ultralytics YOLO to cut food giveaway by 67%

ALYCE accelerates traffic AI inference by 20% with Ultralytics YOLO

Axelera AI delivers 34 FPS edge AI inference using Ultralytics YOLO

Cali Intelligence shortens checkout queues by 43% with Ultralytics YOLO

eSmart Systems halves power line inspection time with Ultralytics YOLO

Kiwitron uses Ultralytics YOLO to detect industrial hazards 30m away

MarineSitu hits 96%+ uptime in underwater monitoring using Ultralytics YOLO

Pixelabs achieves 95% recall with Ultralytics YOLO-driven automation

Prezent boosts slide detection accuracy by 34% with Ultralytics YOLO

SiteAssist improves site safety by processing 770K+ images with Ultralytics YOLO

Specialvideo reaches 99% food inspection accuracy with Ultralytics YOLO

STMicroelectronics runs Ultralytics YOLO on an MCU at just 9.4 mJ per inference

Stride delivers 1-minute equine gait analysis with Ultralytics YOLO

Theia Scientific speeds up microscopy analysis 43× with Ultralytics YOLO

Videologic Analytics scales to 10K AI camera licenses with Ultralytics YOLO

Vivity AI saves $5M+ a year in industrial operations with Ultralytics YOLO

WG Tech Solutions cuts safety violations by 28% with Ultralytics YOLO and Axelera’s AI Accelerator

Chef Robotics uses Ultralytics YOLO to cut food giveaway by 67%

ALYCE accelerates traffic AI inference by 20% with Ultralytics YOLO

Axelera AI delivers 34 FPS edge AI inference using Ultralytics YOLO

Cali Intelligence shortens checkout queues by 43% with Ultralytics YOLO

eSmart Systems halves power line inspection time with Ultralytics YOLO

Kiwitron uses Ultralytics YOLO to detect industrial hazards 30m away

MarineSitu hits 96%+ uptime in underwater monitoring using Ultralytics YOLO

Pixelabs achieves 95% recall with Ultralytics YOLO-driven automation

Prezent boosts slide detection accuracy by 34% with Ultralytics YOLO

SiteAssist improves site safety by processing 770K+ images with Ultralytics YOLO

Specialvideo reaches 99% food inspection accuracy with Ultralytics YOLO

STMicroelectronics runs Ultralytics YOLO on an MCU at just 9.4 mJ per inference

Stride delivers 1-minute equine gait analysis with Ultralytics YOLO

Theia Scientific speeds up microscopy analysis 43× with Ultralytics YOLO

Videologic Analytics scales to 10K AI camera licenses with Ultralytics YOLO

Vivity AI saves $5M+ a year in industrial operations with Ultralytics YOLO

WG Tech Solutions cuts safety violations by 28% with Ultralytics YOLO and Axelera’s AI Accelerator

Chef Robotics uses Ultralytics YOLO to cut food giveaway by 67%

ALYCE accelerates traffic AI inference by 20% with Ultralytics YOLO

Axelera AI delivers 34 FPS edge AI inference using Ultralytics YOLO

Cali Intelligence shortens checkout queues by 43% with Ultralytics YOLO

eSmart Systems halves power line inspection time with Ultralytics YOLO

Kiwitron uses Ultralytics YOLO to detect industrial hazards 30m away

MarineSitu hits 96%+ uptime in underwater monitoring using Ultralytics YOLO

Pixelabs achieves 95% recall with Ultralytics YOLO-driven automation

Prezent boosts slide detection accuracy by 34% with Ultralytics YOLO

SiteAssist improves site safety by processing 770K+ images with Ultralytics YOLO

Specialvideo reaches 99% food inspection accuracy with Ultralytics YOLO

STMicroelectronics runs Ultralytics YOLO on an MCU at just 9.4 mJ per inference

Stride delivers 1-minute equine gait analysis with Ultralytics YOLO

Theia Scientific speeds up microscopy analysis 43× with Ultralytics YOLO

Videologic Analytics scales to 10K AI camera licenses with Ultralytics YOLO

Vivity AI saves $5M+ a year in industrial operations with Ultralytics YOLO

Frequently asked questions

Get started with Ultralytics YOLO!