need help about both model weight and activation quantization with only a float32 mlmodel

from the issue "https://developer.apple.com/forums/thread/740518 how do we use the computational power of A17 Pro Neural Engine?"

I learn that if i want to inference my mlmodel on my ipad pro with m4 soc int8 38T ane high performance, i have to use the coreml torch api to quantize both weight and activation during training time quantization with int8 datatype.

my question is:
I only have a fp32 mlmodel without torch code or model, what can i do?
by the way, if just only weight int8 quantization, M4 ane will use fp16 to compute or int8?
thanks for your help～

Start with the linked Apple Developer forum discussion and the coremltools quantization documentation or APIs. Determine whether an existing float32 .mlmodel can be quantized without the original training code, and clarify the execution behavior of weight-only int8 quantization on the M4 Neural Engine. Done means providing a documented, version-specific answer or identifying the missing prerequisite.

Written by the indexing model from the issue text.