when a plain Python stack is enough with Ollama

[cachebench]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[vrampilot]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

Good point. The pattern around small local stacks has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[sanepeak48]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at structured output. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.