+- 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: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=51)
+---- Thread: simple local serving recipe: setup advice (/showthread.php?tid=200)
Pages:
1
2
simple local serving recipe: setup advice - mlxgarden - 09-10-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of MLX and A6000 felt surprisingly usable once I tuned around quant drift.
Maybe useful as a starting point for newer folks.
Re: simple local serving recipe: setup advice - cacheline - 09-12-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: simple local serving recipe: setup advice - llmpeak - 09-12-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.
Re: simple local serving recipe: setup advice - vramstream - 09-12-2026
My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: simple local serving recipe: setup advice - cachebench - 09-12-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: simple local serving recipe: setup advice - rocmriley - 09-14-2026
that fixed it for me too.
Re: simple local serving recipe: setup advice - rasterbench - 09-14-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: simple local serving recipe: setup advice - mintstation99 - 09-14-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at embeddings. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: simple local serving recipe: setup advice - rocmriley - 09-17-2026
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. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: simple local serving recipe: setup advice - audioriver - 09-18-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?