student models for local use: worth it?

[batchscope72]

Did a small comparison this afternoon. On B200 with Ollama, I saw basically the same behavior.

[quiettoken]

subscribed, curious where this lands.

[torchtrack24]

same here on my side.

[quietstack]

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.