+- 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: routing between local and hosted for Kimi (/showthread.php?tid=372)
Pages:
1
2
routing between local and hosted for Kimi - deepseeked - 09-19-2026
I figured I'd ask here before changing everything.
I'm mostly working with Mixtral in vLLM on M3 Max. The part I'm trying to understand is NVFP4.
Not looking for the perfect answer, mostly what worked in real use.
Re: routing between local and hosted for Kimi - mangovault67 - 09-20-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: routing between local and hosted for Kimi - ggufvault - 09-20-2026
Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: routing between local and hosted for Kimi - sparrowworks88 - 09-21-2026
I'd approach it in a boring order. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: routing between local and hosted for Kimi - emberrunner - 09-24-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: routing between local and hosted for Kimi - griffinloom66 - 09-24-2026
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know the plai
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: routing between local and hosted for Kimi - thetatinker77 - 09-24-2026
Quote:[quote]What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know t
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: routing between local and hosted for Kimi - tensorfield88 - 09-24-2026
Quote:[quote][quote]What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you
A couple things I'd check first. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: routing between local and hosted for Kimi - southtinker - 09-25-2026
same here on my side.
Re: routing between local and hosted for Kimi - deepseeked - 09-25-2026
same here on my side.