+- 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 (/showthread.php?tid=269)
Pages:
1
2
recipes for a good local stack - rocmriley - 09-14-2026
Maybe I'm missing something obvious.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling HBM constraints.
If you've tested something similar, what did you keep and what did you stop bothering with?
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: recipes for a good local stack - rocmriley - 09-14-2026
Quote:Maybe I'm missing something obvious.
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: recipes for a good local stack - audionode8 - 09-14-2026
Good point. I ended up in about the same place using MLX.
Re: recipes for a good local stack - tinycontext - 09-14-2026
Quote:Good point. I ended up in about the same place using MLX.
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: recipes for a good local stack - audioriver - 09-14-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: recipes for a good local stack - rasterbench - 09-16-2026
Good point. I don't think your conclusion is far off.
Re: recipes for a good local stack - relayforge - 09-17-2026
Ran a quick check on my box. On GB200 with SGLang, I saw basically the same behavior. At this point the real bottleneck is my patience.
Re: recipes for a good local stack - mlxgarden - 09-17-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling.
Re: recipes for a good local stack - relayforge - 09-17-2026
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: recipes for a good local stack - vramstream - 09-18-2026
What exact setup are you running? Are you testing this on mini PC or something else?