Kazeia
/
Kazeia-engine
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Correction: 9B CPU ~4.4 (t8 contention), <8B pte; 4B seul GGUF viable

This commit is contained in:
Richard Loyer 2026-05-25 15:54:46 +02:00
parent e462d7ce27
commit 8cc9286f70
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CLAUDE.md
View File

@ -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 = 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. 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.