Probe matrix proved K is the broken side of turbo KV on Qwen3-4B
(QK-norm gamma outliers vs PolarQuant's no-per-channel-range format)
while V tolerates 2-bit for free. Applied to ornith duo main: K q8_0 +
V turbo2 = 128K ctx in ~880MB RAM at full speed (8.7-10.1 t/s concurrent,
vs 3x decode loss with turbo2 K). Qwen duo stays q4/q4 24K — only clean
mix is bigger than q4/q4. InnerQ equalizer confirmed broken as shipped
(compensation error grows with scale strength); documented in
MOE-FINDINGS with the full matrix and fix ladder.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Duo group (resident main+subagent for pi): flip VRAM to the small model.
Ornith experts never touch VRAM; its dense-on-GPU split starved qwen to
176 MiB / 5.8 t/s concurrent. After flip: qwen 43 t/s, ornith 8 t/s.
CUDA_VISIBLE_DEVICES= required for ornith — ngl 0 still allocates ~1GB
pp compute buffer on CUDA builds (OOM+segfault). Duo section in
MOE-FINDINGS.md; also snapshots prior swap-stack migration state.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
mozempkandClaude Fable 5