
HitonabiandClaude Fable 5
e08d812598
Brain-Bench + Latenz-Metrik (Review P1-9/P1-10)
- Bench-Matrix Qwen3.6 (5 Configs, separater Port): MTP n-max 3 bestaetigt (+26% tg),
n-max 4 lohnt nicht, KV Q8_0 gratis (78,6=78,6 t/s) bei halbem KV-Speicher
- deploy-Config: -ctk/-ctv q8_0 am hermes-Eintrag (Live-Schaltung: User-Freigabe noetig)
- voice.py: chat_first_content-Metrik (echte Hirn-Latenz bis erster Inhalts-Token)
- Report um Umsetzungs-Nachtrag ergaenzt
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-02 10:56:23 +02:00
..
2026-06-27 21:25:39 +02:00
2026-06-24 22:17:45 +02:00
2026-06-27 23:26:58 +02:00
2026-06-27 22:16:19 +02:00
2026-06-27 18:23:37 +02:00
2026-07-02 10:56:23 +02:00
2026-06-27 21:25:39 +02:00
2026-06-27 21:25:39 +02:00
2026-06-27 19:24:22 +02:00
2026-06-28 11:52:49 +02:00
2026-06-27 01:54:29 +02:00
2026-06-27 21:25:39 +02:00
2026-06-28 12:02:35 +02:00
2026-06-28 11:52:49 +02:00
2026-06-28 11:52:49 +02:00
2026-06-27 23:26:58 +02:00
2026-06-28 12:02:35 +02:00