when TensorRT-LLM clearly wins with MLX

[macrotinker]

A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Once you know the plain path works, then add the faster path back in piece by piece.

I'm happy to test one more variant if you want a second data point.