---
license: agpl-3.0
pipeline_tag: object-detection
library_name: yolov26
---

# YOLO26-N

Ultralytics YOLO26 is the latest evolution in the YOLO series of real-time object detectors, engineered from the ground up for edge and low-power devices. It introduces a streamlined design that removes unnecessary complexity while integrating targeted innovations to deliver faster, lighter, and more accessible deployment.

## Model Specifications

| Property | Value |
|----------|-------|
| Input Size | 640 pixels |
| mAP (50-95) | 40.9 |
| mAP (50-95, e2e) | 40.1 |
| CPU Speed (ONNX) | 38.9 ms |
| T4 TensorRT10 Speed | 1.7 ms |
| Parameters | 2.4M |
| FLOPs | 5.4B |

## Key Features

The architecture of YOLO26 is guided by three core principles:

**Simplicity:** YOLO26 is a native end-to-end model, producing predictions directly without the need for non-maximum suppression (NMS). By eliminating this post-processing step, inference becomes faster, lighter, and easier to deploy in real-world systems.

**Deployment Efficiency:** The end-to-end design cuts out an entire stage of the pipeline, dramatically simplifying integration, reducing latency, and making deployment more robust across diverse environments.

**Training Innovation:** YOLO26 introduces the MuSGD optimizer, a hybrid of SGD and Muon — inspired by Moonshot AI's Kimi K2 breakthroughs in LLM training. This optimizer brings enhanced stability and faster convergence.

### Additional Highlights

- **DFL Removal:** Simplified inference and broader hardware compatibility
- **End-to-End NMS-Free Inference:** Reduced latency and easier production integration
- **ProgLoss + STAL:** Improved small-object recognition
- **Up to 43% Faster CPU Inference:** Optimized for edge computing

## Usage

Install ultralytics with `pip install ultralytics`.

Download the model.
```python
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="openvision/yolo26-n", filename="model.pt")
```

Infer.
```python
from ultralytics import YOLO
from PIL import Image
import requests

model = YOLO(model_path)

# Train the model on the COCO8 example dataset for 100 epochs
results = model.train(data="coco8.yaml", epochs=100, imgsz=640)

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

# Run inference with the YOLO26n model on the image
results = model.predict(image)
```

## Documentation

For more information, see the [official YOLO26 documentation](https://docs.ultralytics.com/models/yolo26/).