Back to Leaderboard

YOLOv10-N

yolov10

one-stage detector with CSPDarknet backbone

Parameters

2.3M

FLOPs

6.7G

Input Size

640px

License

MIT

Architecture

Type

one-stage

Backbone

CSPDarknet

Neck

PAFPN

Head

NMS-Free

Benchmark Results
Performance on COCO val2017 across different hardware configurations
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)38.4%380.42.6ms148 MB
NVIDIA T4 (TensorRT FP16)38.6%199.95.0ms252 MB
CPU (ONNX Runtime)38.5%28.135.6ms161 MB
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.3ms
1.3ms
0.1ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO

# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolov10n")

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

# Process results
for box in results.boxes:
    print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")
nms-freereal-timeedge-friendly
Notes

No NMS required - fastest end-to-end