image generation model locals actually use with Ollama

[edgequill]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on dual 3090, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[kernelpeak]

Good point. The pattern around KV cache pressure has been pretty similar for me.