+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Video (https://www.datasculpting.ai/inference/forumdisplay.php?fid=70)
+--- Thread: multimodal local stack that feels real (/showthread.php?tid=151)
multimodal local stack that feels real - phasespark - 09-05-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Phi using LM Studio on M3 Max. The headline result was better than I expected, but tokens/sec still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: multimodal local stack that feels real - oxideworks59 - 09-06-2026
A couple things I'd check first. If you're on LM Studio, 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: multimodal local stack that feels real - pixelcrate82 - 09-07-2026
What exact setup are you running? Are you testing this on mini PC or something else?
Re: multimodal local stack that feels real - visionforge - 09-07-2026
I'd start with the simpler stack.
Re: multimodal local stack that feels real - cobalttinker - 09-08-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: multimodal local stack that feels real - turboarch95 - 09-08-2026
I don't think that's the whole story. I've seen people blame batch size when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.