synthetic data for support bots

[routeline23]

I'm trying to sanity-check my setup.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling INT4.

Would appreciate practical advice rather than theory.

I care more about stability than squeezing the last possible tokens/sec out of it.

[plainline]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.