From 025bdd87bd1635037afdfd7979e08e401443d894 Mon Sep 17 00:00:00 2001 From: Richard Loyer Date: Mon, 25 May 2026 18:34:16 +0200 Subject: [PATCH] Briques: 2B 13, 4B 7, 9B 2.1; 2B sweet spot --- CLAUDE.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/CLAUDE.md b/CLAUDE.md index f9887df..6dfa155 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -126,3 +126,6 @@ pte NPU: 15tok/s, 1.7s, 2.2GB. GGUF bridge: 0.32tok/s (1thread+HTP res), 4.5GB. ## CHIFFRES STABLES r3 (les bons) 4B GGUF CPU 9.8±0.24, 9B 5.2±0.18 (t6). r1 anterieurs bruites/throttle (8.4->2.1 invalides). Engine TIENT. pte 4B 15 reste devant. 4B GGUF 9.8 viable, 9B 5.2 si qualite vaut. RAM 4.5/6.8 vs pte 2.2. Toujours bloque in-app affinity 1coeur. Ne plus citer r1. + +## Briques final 2B/4B/9B +2B=13, 4B=7, 9B=2.1tok/s (NPU stack+CPU lm_head). RAM 2.5/3/6.8GB. 9B P4 233ms vocab248k bad. 2B briques 13 sweet spot > engine 4B 9.8/9B 5.2. pour Pierre=2B. JNI206 reste.