Back to Leaderboard
Parameters
0.9M
FLOPs
1.1G
Input Size
640px
License
Apache-2.0
Architecture
Type
one-stage
Backbone
CSPDarknet
Neck
PAFPN
Head
Decoupled
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|
| NVIDIA A100 (TensorRT FP16) | 25.8% | 219.2 | 4.6ms | 39 MB |
| NVIDIA T4 (TensorRT FP16) | 25.9% | 89.7 | 11.1ms | 66 MB |
| CPU (ONNX Runtime) | 25.9% | 11.3 | 88.4ms | 53 MB |
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.3ms
0.8ms
2.5ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO
# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolox-nano")
# Run inference
results = model.predict("image.jpg")
# Process results
for box in results.boxes:
print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")ultra-lightweightedge
Related Models (yolox)