Apple unified memory limits

[mlxgarden]

Thanks, that helps. That matches what I saw on GB200.

[localpatch]

My first guess would be this: If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[mlxgarden]

Thanks, that helps. The pattern around token cost has been pretty similar for me.

[plainember52]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Once you know the plain path works, then add the faster path back in piece by piece. At this point the real bottleneck is my patience.