+- 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 for Mixtral (/showthread.php?tid=281)
model merge got better or just different for Mixtral - torchdesk - 09-14-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between LM Studio and llama.cpp for Llama. The interesting difference for me has been reranking.
Interested in tradeoffs more than fan loyalty.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: model merge got better or just different for Mixtral - emberpeak - 09-16-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
Re: model merge got better or just different for Mixtral - sparrowshed - 09-16-2026
That matches what I was seeing. I ended up in about the same place using LM Studio.
Re: model merge got better or just different for Mixtral - turbosupply83 - 09-16-2026
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece. I keep promising myself this is the last rebuild.
Re: model merge got better or just different for Mixtral - orbitbench6 - 09-17-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: model merge got better or just different for Mixtral - batchember - 09-17-2026
Appreciate the detail. I ended up in about the same place using Ollama.
Re: model merge got better or just different for Mixtral - cozygrid12 - 09-18-2026
same here on my side.