+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Recipes & Configurations (https://www.datasculpting.ai/inference/forumdisplay.php?fid=52)
+---- Thread: model fallback rules that work: setup advice (/showthread.php?tid=127)
Pages:
1
2
Re: model fallback rules that work: setup advice - mellowstream - 09-05-2026
Quote:I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.
Good point. That matches what I saw on mini PC. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: model fallback rules that work: setup advice - cobaltworks25 - 09-05-2026
Quote:Quote:I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.
What exact setup are you running? What model, what runtime, and roughly what context size?