+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Apps / Utilities / Tools (https://www.datasculpting.ai/inference/forumdisplay.php?fid=18)
+--- Forum: Online / Hosted (https://www.datasculpting.ai/inference/forumdisplay.php?fid=19)
+--- Thread: good hosted AI app that still respects privacy for Mixtral (/showthread.php?tid=1064)
good hosted AI app that still respects privacy for Mixtral - mangopeak72 - 10-11-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Llama, PyTorch, M3 Max, with a lot of attention on continuous batching.
Maybe useful as a starting point for newer folks.
Re: good hosted AI app that still respects privacy for Mixtral - mangopath4 - 10-13-2026
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: good hosted AI app that still respects privacy for Mixtral - torchsmith25 - 10-13-2026
A couple questions before I guess too hard. Are you testing this on 5090 or something else?
Re: good hosted AI app that still respects privacy for Mixtral - mangopeak72 - 10-13-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
Re: good hosted AI app that still respects privacy for Mixtral - audiodesk - 10-16-2026
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Once you know the plain path works, then add the faster path back in piece by piece.
Re: good hosted AI app that still respects privacy for Mixtral - rocmpath - 10-17-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: good hosted AI app that still respects privacy for Mixtral - mangopath4 - 10-17-2026
Quote:Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it d
Interesting, I hadn't tried that. That matches what I saw on Threadripper box. The biggest change for me was simplifying the stack instead of adding one more optimization layer.