+- 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 on A6000 (/showthread.php?tid=949)
Pages:
1
2
Re: good hosted AI app that still respects privacy on A6000 - tensorriver - 10-15-2026
Good point. I don't think your conclusion is far off.
Re: good hosted AI app that still respects privacy on A6000 - southpatch - 10-16-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: good hosted AI app that still respects privacy on A6000 - macronest - 10-17-2026
Quote:Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quali
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at speculative decoding. Not glamorous advice, but repeatable baselines save a lot of time.