prompt length getting silly for Phi

[northgarden37]

Did a bit of testing and thought I'd post the result here.

After a few runs on dual 3090, I ended up with decent performance, but the setup only really made sense once I adjusted around NVFP4.

Curious if anyone else landed in the same place.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[thetaarch43]

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.

[audionode8]

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.

That matches what I was seeing. The pattern around tool calling has been pretty similar for me.