+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Model Comparisons (https://www.datasculpting.ai/inference/forumdisplay.php?fid=67)
+--- Thread: image generation model locals actually use with Ollama (/showthread.php?tid=1278)
image generation model locals actually use with Ollama - edgequill - 10-15-2026
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.
Re: image generation model locals actually use with Ollama - kernelpeak - 10-16-2026
Good point. The pattern around KV cache pressure has been pretty similar for me.