After converting to the coreml model, the inference speed is still lower than that of the previous yolo11

[119458]

Search before asking

• [x] I have searched the Ultralytics YOLO issues and discussions and found no similar questions.

Question

`from ultralytics import YOLO

model = YOLO("yolo26n.pt")

model.export(format="coreml")`

The increase in computing units on the cpu leads to a slower inference speed

For the same model, the inference speed of yolo11n is 1.45ms, with a time difference of 1ms.

Additional

No response