reranking still worth it for small sets

[minthall]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. Once yo

Interesting, I hadn't tried that. I don't think your conclusion is far off.

[torchkite]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[quantshed]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[oxidegrove40]

My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[bytesupply76]

Not sure I agree there. 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.