+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Agents (https://www.datasculpting.ai/inference/forumdisplay.php?fid=44)
+--- Thread: student models for local use: worth it? (/showthread.php?tid=350)
Pages:
1
2
Re: student models for local use: worth it? - batchscope72 - 09-25-2026
Did a small comparison this afternoon. On B200 with Ollama, I saw basically the same behavior.
Re: student models for local use: worth it? - quiettoken - 09-26-2026
subscribed, curious where this lands.
Re: student models for local use: worth it? - torchtrack24 - 09-29-2026
same here on my side.
Re: student models for local use: worth it? - quietstack - 09-29-2026
I'd approach it in a boring order. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.