+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Dataset Creation / Curation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=56)
+--- Thread: reranking still worth it for small sets (/showthread.php?tid=577)
reranking still worth it for small sets - phasenode - 09-29-2026
Spent some time on this today and wanted to compare notes.
I'm comparing two approaches here: keep it simple on A6000, or squeeze more out of the stack and deal with the complexity.
Interested in tradeoffs more than fan loyalty.
Re: reranking still worth it for small sets - plainscope50 - 09-30-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: reranking still worth it for small sets - labnest - 09-30-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: reranking still worth it for small sets - deepseeked - 10-01-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
Re: reranking still worth it for small sets - mlxgarden - 10-01-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: reranking still worth it for small sets - batchfield55 - 10-04-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Once you know the plain path works, then add the faster path back in piece by piece.