YOLO11

yolo11

External baseline · 2024

Variants5

Parameters2.6M - 56.9M

Best Paper mAP54.7%

Licensenon-permissive

Model Variants

All variants benchmarked on COCO val2017. Click any variant for the full hardware breakdown.

Model	Params	GFLOPs	Paper mAP	Best FPS
YOLO11-N	2.6M	6.5	39.5%	53 FPS NVIDIA Jetson Orin Nano Super 8GB · TensorRT FP16	Details
YOLO11-S	9.4M	21.5	47%	41 FPS NVIDIA Jetson Orin Nano Super 8GB · TensorRT FP16	Details
YOLO11-M	20.1M	68.0	51.5%	26 FPS NVIDIA Jetson Orin Nano Super 8GB · TensorRT FP16	Details
YOLO11-L	25.3M	86.9	53.4%	23 FPS NVIDIA Jetson Orin Nano Super 8GB · TensorRT FP16	Details
YOLO11-X	56.9M	194.9	54.7%	16 FPS NVIDIA Jetson Orin Nano Super 8GB · TensorRT FP16	Details

Architecture

Type

one-stage

Backbone

CSPDarknet

Neck

C3k2-PAFPN

Head

Decoupled

anchor-freenmsTrained on COCO train2017

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