RAG recall vs speed tradeoff with LM Studio

[macrotinker]

Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around TensorRT-LLM and mini PC.

Would rather learn from your scars than collect my own all at once.

This is mostly for local work rather than public serving.

If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.