image generation model locals actually use with vLLM

[vrampilot]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.