diff --git a/CLAUDE.md b/CLAUDE.md index 6de1542..0faa41d 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -84,3 +84,6 @@ Qwen3.5-9B-Q4_0: prefill HTP 41 / decode CPU 8.4 / 5GB. 30B-A3B Q3 13GB=OOM (11. ## Cascade 9B+Guard4B = PASSE (24/05) Speaker 9B 5GB + Thinker Guard-4B 2.5GB = 7.5GB co-resident, 8GB libre. Guard-8B(4.5)+9B=9.5GB ok aussi. +TTS/STT 2GB OK. Guard=qwen3 dense pref22/dec11; 9B pref41/dec8.4. Cascade ~2s+5-8s. Tient sur 16GB. vs 30B/35B OOM. + +## Cascade speed/qualite (24/05) +9B+Guard4B: thinker dec11/speaker8.4, 7.5GB, ~9s/tour. 9B+Guard8B: 7.2/8.4, 9.5GB, ~11s. Les 2 FR coherent. Reco=Guard4B (marge+vitesse). Texte cote-a-cote: cli/completion instables (DSP mapping fail satur), vraie eval qualite = harness JNI. fits confirmes.