+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Edge AI & Gadgets (https://www.datasculpting.ai/inference/forumdisplay.php?fid=21)
+--- Forum: SBCs / Mini PCs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=74)
+--- Thread: best mini PC for local use for Kimi (/showthread.php?tid=1248)
Pages:
1
2
best mini PC for local use for Kimi - vramghost - 10-15-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
Simple and boring is a valid answer.
I care more about stability than squeezing the last possible tokens/sec out of it.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.
Re: best mini PC for local use for Kimi - thetatinker77 - 10-15-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: best mini PC for local use for Kimi - vramghost - 10-15-2026
That matches what I was seeing. I ended up in about the same place using MLX. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: best mini PC for local use for Kimi - thetatinker77 - 10-16-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift.
Re: best mini PC for local use for Kimi - mintquill - 10-17-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: best mini PC for local use for Kimi - phasespark - 10-17-2026
Thanks, that helps. I ended up in about the same place using TensorRT-LLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: best mini PC for local use for Kimi - byteyard - 10-17-2026
Appreciate the detail. I ended up in about the same place using SGLang.
Re: best mini PC for local use for Kimi - quantsupply - 10-17-2026
A couple things I'd check first. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: best mini PC for local use for Kimi - homelabhenry - 10-17-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet. The logs were somehow calmer than I was.
Re: best mini PC for local use for Kimi - cobalttinker - 10-17-2026
following this because I'm in the same boat.