From f82fa6128182479aa0fc5d8e1f7d00387510e70c Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Sun, 24 May 2026 19:13:20 +0200
Subject: [PATCH] 9B: 41/8.4 5GB tient; 30B/35B OOM. Plafond=9B+4B parallele,
 MoE hors-jeu

---
 CLAUDE.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CLAUDE.md b/CLAUDE.md
index a0e26bd..74f60cb 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -78,3 +78,6 @@ HMX on/off=54.7 identique, b1024=54.7 -> GDN scalaire = ancre (pas matmul). Plaf
 
 ## Plafond prefill: HVX deja actif, inutile (55.5=55.9 scalar=hvx)
 Mur = dependance serielle 512tok, pas calcul. HVX inner-dot ~0 gain. Cap 55 = recurrence. Seul levier = chunkwise GDN (delta rule matricielle->HMX->~100), changement algo, semaines, bit-exact frontiere. Aucun gain rapide. decode 15 fige.
+
+## 9B + verdict gros modeles (24/05)
+Qwen3.5-9B-Q4_0: prefill HTP 41 / decode CPU 8.4 / 5GB. 30B-A3B Q3 13GB=OOM (11.7 dispo). 35B FP8/Int4 non-GGUF+ne tient pas. Plafond tablette: 9B seul ou 9B+4B parallele. MoE hors-jeu. Decode BW: 4B=15,9B=8.4. Fix GDN s applique au 9B.