Back to Leaderboard

YOLOv11-X

yolov11

one-stage detector with C3K2 backbone

Parameters

56.9M

FLOPs

195.0G

Input Size

640px

License

MIT

Architecture

Type

one-stage

Backbone

C3K2

Neck

SPPF

Head

Decoupled

Benchmark Results
Performance on COCO val2017 across different hardware configurations
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)54.6%69.214.4ms2418 MB
NVIDIA T4 (TensorRT FP16)54.7%26.937.2ms2522 MB
CPU (ONNX Runtime)54.8%3.0334.0ms2443 MB
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.2ms
10.6ms
2.6ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO

# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolov11x")

# Run inference
results = model.predict("image.jpg")

# Process results
for box in results.boxes:
    print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")
latesthighest-accuracy
Related Models (yolov11)