quant support gaps for Mixtral

[labline]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher.

I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[tensorworks]

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

[routecrate]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?