+- 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: recipes for a good local stack with MLX (/showthread.php?tid=1213)
recipes for a good local stack with MLX - mintstation99 - 10-15-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on A6000, I ended up with decent performance, but the setup only really made sense once I adjusted around batch size.
Nothing scientific here, just practical notes from a real setup.
This is mostly for local work rather than public serving.
The part that surprised me was how much the boring details mattered more than the model choice.
Re: recipes for a good local stack with MLX - vectorfield - 10-16-2026
Quote:Did a bit of testing and thought I'd post the result here.
I don't think that's the whole story. I've seen people blame prefill/decode split when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: recipes for a good local stack with MLX - rocmriley - 10-16-2026
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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: recipes for a good local stack with MLX - kernelgrid - 10-16-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Re: recipes for a good local stack with MLX - rocmriley - 10-16-2026
That matches what I was seeing. 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: recipes for a good local stack with MLX - cachebench - 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. Could be a workload difference, but I wouldn't generalize too fast from one setup. I keep promising myself this is the last rebuild.
Re: recipes for a good local stack with MLX - rocmhouse90 - 10-18-2026
That matches what I was seeing. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: recipes for a good local stack with MLX - kernelpeak - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there.
Re: recipes for a good local stack with MLX - rocmriley - 10-19-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.