Same model Deepseek V4 Flash 0731 tested with different AI harnesses, huge RAM usage difference and only 2 harness were able to find a valid solution for the task.
source & further reading
grigio.org — original article
Sonia - Local Voice Assistant in less than 13Gb RAM, NO Dedicated GPU, Skills/Tool-calling supported
Pi Coding Agent and Jev integration use cases
Does harness evolution generalize? Notes on Google's RRSI paper