+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: MCP / APIs / Tool Calling (https://www.datasculpting.ai/inference/forumdisplay.php?fid=46)
+--- Thread: model merge got better or just different: anyone testing this? (/showthread.php?tid=57)
model merge got better or just different: anyone testing this? - fastfield4 - 08-28-2026
Did a bit of testing and thought I'd post the result here.
Short version: llama.cpp behaved well for me, but only after I stopped ignoring speculative decoding.
Curious if anyone else landed in the same place.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: model merge got better or just different: anyone testing this? - deltagrid - 08-28-2026
Appreciate the detail. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: model merge got better or just different: anyone testing this? - thetaarch43 - 08-28-2026
that fixed it for me too.