Verdict

RF-DETR-N is 0.7 mAP points more accurate, 51.4 vs 50.7 mAP@50-95 on COCO val2017. RT-DETRv2-R18 is faster on desktop GPU, 51.1 vs 39.5 FPS on an RTX 5070 Ti, and leads on small objects. The input sizes differ: RF-DETR-N runs at 384 px and RT-DETRv2-R18 at 640 px, each at its author default. On Raspberry Pi 5 the speed order flips and RF-DETR-N is faster.

This is not a like-for-like resolution test. RF-DETR-N (30.47M parameters, Apache-2.0) is evaluated at 384 px; RT-DETRv2-R18 (20.18M, Apache-2.0) at 640 px, each at its default input size. Both run on COCO val2017 with verified rows on desktop GPU, Jetson Orin, and Raspberry Pi 5. Treat the numbers as each model at its own recommended setting. For every variant of both families, see the RF-DETR vs RT-DETR family comparison.

MetricRF-DETR-NRT-DETRv2-R18
mAP@50-9551.450.8
mAP@5069.967.4
mAP small27.733.5
FPS (mean)39.551.1
Total ms/image25.3019.55
Inference ms16.9814.82
Peak VRAM (MB)151169
Params (M)30.520.2
GFLOPs-60.0
Input size384640
LicenseApache-2.0Apache-2.0
RF-DETR-N vs RT-DETRv2-R18 on NVIDIA RTX 5070 Ti, PyTorch FP32, batch 1. mAP shown in percent form.
Live chartverified data
Accuracy vs parameters on COCO val2017. RF-DETR-N (384 px) and RT-DETRv2-R18 (640 px) highlighted against the full field.

Accuracy

mAP is shown in percent form. RF-DETR-N measures 51.4 mAP@50-95 to RT-DETRv2-R18's 50.7, a 0.7 point edge. RT-DETRv2-R18 leads on small objects: 33.5 vs 27.7 mAP_small, a 17.32% relative gap. If small instances dominate your scenes, RT-DETRv2-R18 is the safer pick.

Speed

On the RTX 5070 Ti in PyTorch, RT-DETRv2-R18 runs 51.1 FPS to RF-DETR-N's 39.5, so it is 22.72% faster. The margin grows under conversion: 97.1 vs 65.7 FPS on ONNX Runtime and 125.5 vs 67.6 FPS on TensorRT FP32. On Jetson Orin the two are level at 10.3 vs 10.2 FPS.

The speed verdict flips on Raspberry Pi 5, where RF-DETR-N runs 2.1 FPS to RT-DETRv2-R18's 0.8. If your target is a bare Pi, the desktop numbers point the wrong way.

License and provenance
RF-DETR-N license
Apache-2.0
RT-DETRv2-R18 license
Apache-2.0
RF-DETR-N release
2026-02-23
RT-DETRv2-R18 release
2024-05-01
RF-DETR-N input
384 px
RT-DETRv2-R18 input
640 px
Evaluated weights
LibreYOLO retrained checkpoints

When to pick which

Pick RF-DETR-N for CPU-bound edge targets like the Raspberry Pi 5, where it is the faster detector, and where its lower VRAM helps. Pick RT-DETRv2-R18 for GPU throughput and for small-object accuracy. Both are Apache-2.0, so licensing does not force the choice.

Every number on this page comes from the verified dataset: same 500-image COCO val2017 slice, conf 0.001, IoU 0.6, max 300 detections, pycocotools mAP, identical protocol across all hardware and runtimes. The full protocol is on the methodology page. To rerun this comparison with your own filters, open compare. Accuracy is measured on LibreYOLO retrained checkpoints; other weight sources can yield different values.