+- 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: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=51)
+---- Thread: simple local serving recipe: anyone testing this? (/showthread.php?tid=263)
Pages:
1
2
Re: simple local serving recipe: anyone testing this? - cachebench - 09-19-2026
My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: simple local serving recipe: anyone testing this? - rocmhouse90 - 09-20-2026
Quote:My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamor
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: simple local serving recipe: anyone testing this? - mangoquill - 09-20-2026
I hit almost the same issue last night.
Re: simple local serving recipe: anyone testing this? - mlxgarden - 09-23-2026
That matches what I was seeing. I don't think your conclusion is far off.