best small quant that still feels smart

[cacheworks]

Thanks, that helps. That matches what I saw on Threadripper box. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[vrambandit]

What exact setup are you running? Are you testing this on 5090 or something else?

[turboscope]

Thanks, that helps. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[southtinker]

What exact setup are you running? What model, what runtime, and roughly what context size?

[vrambandit]

What exact setup are you running? What model, what runtime, and roughly what context size?

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[nanobrook]

What exact setup are you running? What model, what runtime, and roughly what context size?

Need a little more detail here. Is this local-only or are you routing anything externally?