# YOLOX-M

> YOLOX-M: one-stage object detector from the YOLOX family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: YOLOX (Megvii)
- Parameters: 25.3M
- GFLOPs: 37.0
- Default input size: 640px
- Detection: anchor-free · nms
- Architecture: one-stage · CSPDarknet backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 46.9%
- Paper: https://arxiv.org/abs/2107.08430
- Original code: https://github.com/Megvii-BaseDetection/YOLOX

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 51.8 | 9.3 | 107.3 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 51.7 | 9.1 | 110.1 | 172 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 51.8 | 28.0 | 35.7 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 51.8 | 16.4 | 61.1 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 51.8 | 55.8 | 17.9 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 51.7 | 48.2 | 20.7 | 172 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 51.6 | 83.0 | 12.0 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 51.7 | 70.1 | 14.3 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreYOLOXm.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

Source: https://www.visionanalysis.org/model/yolox-m. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).