+- 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=347)
model merge got better or just different for Mixtral - bytelab - 09-18-2026
Did a bit of testing and thought I'd post the result here.
I tried this with DeepSeek using SGLang on B200. The headline result was better than I expected, but batch size still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
Re: model merge got better or just different for Mixtral - bytesupply76 - 09-18-2026
Interesting, I hadn't tried that. The pattern around workstation thermals has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: model merge got better or just different for Mixtral - batchyard - 09-18-2026
following this because I'm in the same boat.