+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: News & Industry (https://www.datasculpting.ai/inference/forumdisplay.php?fid=26)
+--- Thread: industry move that matters for local users (/showthread.php?tid=139)
Pages:
1
2
industry move that matters for local users - quietstack - 09-04-2026
Spent some time on this today and wanted to compare notes.
I'm comparing two approaches here: keep it simple on M3 Max, or squeeze more out of the stack and deal with the complexity.
What would you pick if you had to live with it for a few months? At this point the real bottleneck is my patience.
Re: industry move that matters for local users - orbitgarden - 09-04-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: industry move that matters for local users - phaseshed - 09-05-2026
worth checking the driver first.
Re: industry move that matters for local users - amberrunner - 09-05-2026
Quote:worth checking the driver first.
same here on my side.
I'm happy to test one more variant if you want a second data point.
Re: industry move that matters for local users - deepseeked - 09-06-2026
Interesting, I hadn't tried that. I ended up in about the same place using vLLM.
Re: industry move that matters for local users - bytelab - 09-06-2026
I'd start with the simpler stack.
Re: industry move that matters for local users - modbench - 09-06-2026
Thanks, that helps. 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: industry move that matters for local users - deepseeked - 09-07-2026
Appreciate the detail. That matches what I saw on mini PC.
Re: industry move that matters for local users - bytestack - 09-08-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.
Re: industry move that matters for local users - fastlab - 09-09-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.