Object Detection speed decreased moving from ML.NET 1.7.0 to 3.0

**System Information (please complete the following information):**
- OS & Version: Windows 11
- ML.NET Version: ML.NET 1.7.0 and 3.0
- .NET Version: .NET 8

**Describe the bug**
I trained my model last year, with ML Model Builder and ML.NET 1.7 with a set of images annotated with VOTT. The training was in Azure because at that time it wasn't possible to train locally. Then I produced the console sample application that loads my ONNX MLModel1.zip.
With a reference image, after the first load, it takes 0.58s on my current machine to detect the objects.
My computer has GPU but I assume it's not used at this stage.

I retrained my model now, this time locally, with my GPU, with the same image set and annotations, and a file MLModel1.mlnet is created, and the sample console app has tochsharp nuget instead of onnx nugets.
If I test (after first load) with
mlContext.GpuDeviceId = null;
mlContext.FallbackToCpu = true;
now it takes 2.1s
If I test (after first load) with
mlContext.GpuDeviceId = 0;
mlContext.FallbackToCpu = false;
now it takes 0.68s

The older version, even without using CPU, is faster.

**To Reproduce**
Steps to reproduce the behavior:

**Expected behavior**
An improvement

**Screenshots, Code, Sample Projects**
The image I use as reference