Same model, same Q4_K_M label: 5.02, 5.07 and 5.27 bits per weight

Does this catch intermittent fallback between requests?

	▲	logickkk1 an hour ago \| parent [-]
		Yes, picchio monitors a running llama-server on a timer and flags when the prefill/decode ratio goes CPU-shaped. I hot-swapped one mid-run. probe 4 caught ENGAGED -> NOT ENGAGED.