Back to Leaderboard
YOLOv11-S
yolov11one-stage detector with C3K2 backbone
Parameters
9.4M
FLOPs
21.5G
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
| Hardware | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|
| NVIDIA A100 (TensorRT FP16) | 46.9% | 171.6 | 5.8ms | 515 MB |
| NVIDIA T4 (TensorRT FP16) | 47.0% | 63.6 | 15.7ms | 496 MB |
| CPU (ONNX Runtime) | 47.1% | 8.3 | 119.9ms | 535 MB |
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.0ms
2.3ms
2.5ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO
# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolov11s")
# Run inference
results = model.predict("image.jpg")
# Process results
for box in results.boxes:
print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")latestbalanced