simple local serving recipe: anyone testing this?

[cachebench]

My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[rocmhouse90]

My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamor

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[mangoquill]

I hit almost the same issue last night.

[mlxgarden]

That matches what I was seeing. I don't think your conclusion is far off.