From 8cc9286f70e7b00113a3aae5ab38373adb639c6e Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Mon, 25 May 2026 15:54:46 +0200
Subject: [PATCH] Correction: 9B CPU ~4.4 (t8 contention), <8B pte; 4B seul
 GGUF viable

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

diff --git a/CLAUDE.md b/CLAUDE.md
index 93f1007..337e6f6 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -120,3 +120,6 @@ pte NPU: 15tok/s, 1.7s, 2.2GB. GGUF bridge: 0.32tok/s (1thread+HTP res), 4.5GB.
 
 ## 9B = vraie cible (pas de pte 9B)
 9B in-app: CPU 11%=1 coeur (n_threads=8 perdu), 0.16tok/s, 6.8GB. standalone t8=8.4=~8s/tour utilisable. 8B pte 3GB existe vs 9B GGUF 6.8GB. merge 9B tient a t8 effectif. cap64 borne hang. Bench 8B pte vs 9B gguf qualite=vrai arbitrage. dev: forcer affinity 8 grands coeurs.
+
+## CORRECTION 9B: t4=4.4 t8=2.1 (contention), pas 8.4
+9B GGUF plafond ~4.4tok/s 14s/tour < 8B pte 9.75. 9B non convaincant. 4B GGUF seul viable t8=13. Cascade=Guard4B+4B. merge#277 = affinity 8 coeurs pour 4B. 9B=ecarte. mon 8.4 anterieur=errone.