+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: General (https://www.datasculpting.ai/inference/forumdisplay.php?fid=25)
+--- Thread: what made local AI click for you (/showthread.php?tid=330)
Pages:
1
2
what made local AI click for you - quiettoken - 09-18-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about prefix caching.
Simple and boring is a valid answer.
Re: what made local AI click for you - quiettoken - 09-18-2026
Quote:Posting this in case it saves someone else a little time.
Thanks, that helps. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: what made local AI click for you - dockember - 09-18-2026
That matches what I was seeing. That matches what I saw on Threadripper box.
Re: what made local AI click for you - ggufwire22 - 09-18-2026
Thanks, that helps. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: what made local AI click for you - rocmplane - 09-21-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: what made local AI click for you - quiettoken - 09-21-2026
Interesting, I hadn't tried that. That matches what I saw on Threadripper box. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: what made local AI click for you - ggufwire22 - 09-21-2026
A couple things I'd check first. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: what made local AI click for you - rocmplane - 09-21-2026
I hit almost the same issue last night.
Re: what made local AI click for you - pixelcrate82 - 09-21-2026
My first guess would be this: On 5090, 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: what made local AI click for you - rocmplane - 09-22-2026
I'd start with the simpler stack. I keep promising myself this is the last rebuild.