+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: RAG (https://www.datasculpting.ai/inference/forumdisplay.php?fid=58)
+--- Thread: where reranking mattered (/showthread.php?tid=1315)
where reranking mattered - kernelghost - 10-16-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: MLX on GB200, keeping HBM constraints in mind from the start.
If someone wants the exact settings I can clean them up and post them.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: where reranking mattered - modrunner27 - 10-16-2026
A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: where reranking mattered - homelabhenry - 10-17-2026
That matches what I was seeing. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer. I keep promising myself this is the last rebuild.
Re: where reranking mattered - deltastation - 10-17-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.
Re: where reranking mattered - tinycontext - 10-18-2026
worth checking the driver first.
Re: where reranking mattered - quietsupply11 - 10-19-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: where reranking mattered - bytelab - 10-19-2026
That matches what I was seeing. The pattern around embeddings has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable. At this point the real bottleneck is my patience.
Re: where reranking mattered - phasenode - 10-19-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks.
Re: where reranking mattered - turbogrid11 - 10-19-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: where reranking mattered - homelabhenry - 10-19-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?