YOLO26-N

yolo26Coming Soon

one-stage detector with CSPDarknet backbone

Parameters2.4M

GFLOPs5.4

Input Size640px

Best mAP40.1%

Licensenon-permissive

Architecture

Type

one-stage

Backbone

CSPDarknet

Neck

PAFPN

Head

NMS-Free End-to-End

Benchmark Results

Performance on COCO val2017 across different hardware configurations

Hardware	Runtime	mAP@50-95	FPS	Latency	VRAM
NVIDIA Jetson Orin Nano Super 8GB	ONNX Runtime FP32	40.1%	10.4	96.5ms	-
NVIDIA Jetson Orin Nano Super 8GB	PyTorch FP32	40.1%	21.6	46.4ms	119 MB
NVIDIA Jetson Orin Nano Super 8GB	TensorRT FP16	40.1%	60.2	16.6ms	11 MB
Raspberry Pi 5	ncnn FP32	40.1%	12.9	77.6ms	-
Raspberry Pi 5	ONNX Runtime FP32	40.1%	7.1	140.6ms	-
Raspberry Pi 5	PyTorch FP32	40.1%	5.0	198.1ms	-

Speed Breakdown(NVIDIA Jetson Orin Nano Super 8GB)

7.0ms

82.9ms

0.8ms

Preprocess

Inference

Postprocess (NMS)

anchor-freenms-freePaper: 40.9% mAP

Related Models (yolo26)

YOLO26-S YOLO26-M YOLO26-L YOLO26-X

Run any model with one line

LibreYOLO has the best catalogue of state-of-the-art detectors, all behind one MIT-licensed Python API.

from libreyolo import LibreYOLO, SAMPLE_IMAGE # LibreYOLO has the best catalogue of state-of-the-art models. model = LibreYOLO("LibreRFDETRl.pt") # RF-DETR-L (transformer flagship) results = model(SAMPLE_IMAGE, save=True) # run inference, save the annotated image # Swap in any other model, same one-line API (weights auto-download): # LibreYOLO("LibreYOLO9c.pt") # YOLO9-C # LibreYOLO("LibreYOLOXx.pt") # YOLOX-X # LibreYOLO("LibreDFINEx.pt") # D-FINE-X # LibreYOLO("LibreRTDETRr50.pt") # RT-DETR-R50