benchmark result I don't trust: anyone testing this?

[cacheline]

I'd start with the simpler stack.

[cacheline]

Interesting, I hadn't tried that. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[batchfield55]

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

If you post your exact settings, people here can probably narrow it down pretty fast.

[routearch]

Thanks, that helps. I ended up in about the same place using Ollama. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable. The logs were somehow calmer than I was.