docs(frank-small): Q8_0 rung evaluated and closed — floor break plus -24% decode

2026-10-04 18:17:43 -07:00
parent c4603b130c
commit a1c4701d7e
1 changed files with 10 additions and 0 deletions
@@ -54,6 +54,16 @@ field, never `total − used`: the driver holds ~450 MiB of reserve the
 subtraction hides (that error once overstated this card's slack by a
 half-GiB).

+**Quant ceiling, evaluated and closed 2026-10-03 (Frank: stay here).**
+`Q8_0` is the only rung above this one on the Hub (9,545,979,424 B = 9,104
+MiB, +1,671 over Q6_K): at the live pool it would leave 1,178 MiB free —
+under the floor — and the calibrated bandwidth law (it predicted this file's
+94.4 t/s from Q5_K_M's 104.84 within 1 %) puts decode at ~72 t/s, a further
+−24 % for the near-lossless rung. Fitting it was priced two ways (trim the
+pool to 2 × 182,272 — which also breaks frank-large's 183,501-token
+compaction-prompt fit by 1,236 tokens — or revert V to `q8_0`), and both
+were declined. Re-open only on evidence the Q6_K residual matters.
+
 **Pool prices on this card come from boots, never formulas** — the measured
 boot-pair table lives in [[frank-small-llama-mimo-q5km]] (*Shape and KV
 contract*) and still prices every rollback shape.