+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Proprietary / Frontier (https://www.datasculpting.ai/inference/forumdisplay.php?fid=48)
+--- Thread: best local open-weight model this week for Kimi (/showthread.php?tid=222)
Pages:
1
2
best local open-weight model this week for Kimi - amberhall - 09-11-2026
This keeps coming up in conversation so I figured I'd start a thread.
One thing I keep noticing is that people underestimate KV cache pressure until they actually try to run this stuff for more than one afternoon.
Curious whether that lines up with what other people are seeing.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: best local open-weight model this week for Kimi - northquill - 09-11-2026
Appreciate the detail. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: best local open-weight model this week for Kimi - kernelmike - 09-11-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: best local open-weight model this week for Kimi - latentpeak22 - 09-11-2026
worth checking the driver first.
Re: best local open-weight model this week for Kimi - southpatch - 09-12-2026
worth checking the driver first.
Re: best local open-weight model this week for Kimi - torchtrack24 - 09-13-2026
Quote:worth checking the driver first.
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: best local open-weight model this week for Kimi - amberpatch25 - 09-13-2026
Appreciate the detail. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: best local open-weight model this week for Kimi - cobaltspark - 09-13-2026
following this because I'm in the same boat.
Re: best local open-weight model this week for Kimi - tinycontext - 09-13-2026
same here on my side.
Re: best local open-weight model this week for Kimi - fastfield4 - 09-15-2026
What worked for me was pretty simple. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.