Back to Leaderboard

YOLO-NAS-L

yolo-nas

one-stage detector with NAS-Optimized backbone

Parameters

44.5M

FLOPs

121.2G

Input Size

640px

License

Apache-2.0

Architecture

Type

one-stage

Backbone

NAS-Optimized

Neck

QSP

Head

Decoupled

Benchmark Results
Performance on COCO val2017 across different hardware configurations
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)52.3%91.810.9ms1801 MB
NVIDIA T4 (TensorRT FP16)52.2%34.628.9ms1860 MB
CPU (ONNX Runtime)52.2%4.0252.9ms1813 MB
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.3ms
7.2ms
2.4ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO

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

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

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