Your workflow is unusual, oftentimes there is a vigorous back and forth, or a desired output like code generation, etc where a low tk/s drastically effects ux and user productivity.
But the real kicker here is the 90s ttft, that means you ask a question and don't see anything for a full minute and a half.
But the real kicker here is the 90s ttft, that means you ask a question and don't see anything for a full minute and a half.