Inference
when RAG was overkill on 5090 - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Distillation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=55)
+--- Thread: when RAG was overkill on 5090 (/showthread.php?tid=929)

Pages: 1 2


Re: when RAG was overkill on 5090 - vrambandit - 10-12-2026

Quote:My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain pa

Appreciate the detail. That matches what I saw on dual 3090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.


Re: when RAG was overkill on 5090 - cozywire - 10-12-2026

What exact setup are you running? Are you testing this on mini PC or something else?