small speech stack for local use: setup advice

[llmtrack]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.

[deltastation]

Appreciate the detail. That matches what I saw on B200.

[bytegarden73]

Need a little more detail here. What model, what runtime, and roughly what context size?

[vramarch]

Thanks, that helps. The pattern around KV cache pressure has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.