+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: Systems & Builds (https://www.datasculpting.ai/inference/forumdisplay.php?fid=29)
+--- Thread: power delivery for 24/7 serving (/showthread.php?tid=112)
Pages:
1
2
Re: power delivery for 24/7 serving - homelabhenry - 09-06-2026
subscribed, curious where this lands.
Re: power delivery for 24/7 serving - plainscope50 - 09-06-2026
Quote:subscribed, curious where this lands.
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Re: power delivery for 24/7 serving - homelabhenry - 09-06-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: power delivery for 24/7 serving - phasenode - 09-06-2026
Need a little more detail here. What model, what runtime, and roughly what context size?
Re: power delivery for 24/7 serving - batchwire - 09-06-2026
I hit almost the same issue last night.