Export Table

{%set tip1 = ':material-information-outline:{ title="conf, iou, agnostic_nms are also available when nms=True" }' %} {%set tip2 = ':material-information-outline:{ title="IMX format is currently only supported for YOLOv8n, YOLO11n models" }' %}

Format	format Argument	Model	Metadata	Arguments
PyTorch	-	{{ model_name or "yolo26n" }}.pt	✅	-
TorchScript	torchscript	{{ model_name or "yolo26n" }}.torchscript	✅	imgsz, half, dynamic, optimize, nms{{ tip1 }}, batch, device
ONNX	onnx	{{ model_name or "yolo26n" }}.onnx	✅	imgsz, half, dynamic, simplify, opset, nms{{ tip1 }}, batch, device
OpenVINO	openvino	{{ model_name or "yolo26n" }}_openvino_model/	✅	imgsz, half, dynamic, int8, nms{{ tip1 }}, batch, data, fraction, device
TensorRT	engine	{{ model_name or "yolo26n" }}.engine	✅	imgsz, half, dynamic, simplify, workspace, int8, nms{{ tip1 }}, batch, data, fraction, device
CoreML	coreml	{{ model_name or "yolo26n" }}.mlpackage	✅	imgsz, dynamic, half, int8, nms{{ tip1 }}, batch, device
TF SavedModel	saved_model	{{ model_name or "yolo26n" }}_saved_model/	✅	imgsz, keras, int8, nms{{ tip1 }}, batch, data, fraction, device
TF GraphDef	pb	{{ model_name or "yolo26n" }}.pb	❌	imgsz, batch, device
TF Lite	tflite	{{ model_name or "yolo26n" }}.tflite	✅	imgsz, half, int8, nms{{ tip1 }}, batch, data, fraction, device
TF Edge TPU	edgetpu	{{ model_name or "yolo26n" }}_edgetpu.tflite	✅	imgsz, int8, data, fraction, device
TF.js	tfjs	{{ model_name or "yolo26n" }}_web_model/	✅	imgsz, half, int8, nms{{ tip1 }}, batch, data, fraction, device
PaddlePaddle	paddle	{{ model_name or "yolo26n" }}_paddle_model/	✅	imgsz, batch, device
MNN	mnn	{{ model_name or "yolo26n" }}.mnn	✅	imgsz, batch, int8, half, device
NCNN	ncnn	{{ model_name or "yolo26n" }}_ncnn_model/	✅	imgsz, half, batch, device
IMX500{{ tip2 }}	imx	{{ model_name or "yolo26n" }}_imx_model/	✅	imgsz, int8, data, fraction, nms{{ tip1 }}, device
RKNN	rknn	{{ model_name or "yolo26n" }}_rknn_model/	✅	imgsz, batch, name, device
ExecuTorch	executorch	{{ model_name or "yolo26n" }}_executorch_model/	✅	imgsz, batch, device
Axelera	axelera	{{ model_name or "yolo26n" }}_axelera_model/	✅	imgsz, batch, int8, data, fraction, device