Back to Leaderboard
Parameters
32.0M
FLOPs
110.0G
Input Size
640px
License
Apache-2.0
Architecture
Type
transformer
Backbone
HGNetv2
Neck
HybridEncoder
Head
DETR
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|
| NVIDIA A100 (TensorRT FP16) | 52.9% | 92.9 | 10.8ms | 1447 MB |
| NVIDIA T4 (TensorRT FP16) | 52.9% | 34.7 | 28.8ms | 1490 MB |
| CPU (ONNX Runtime) | 53.1% | 4.2 | 235.9ms | 1407 MB |
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.2ms
7.1ms
2.5ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO
# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/rtdetr-l")
# Run inference
results = model.predict("image.jpg")
# Process results
for box in results.boxes:
print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")transformerno-nmsefficient
Related Models (rtdetr)