2 commits

Author	SHA1	Message	Date
xray	c1a984b22b	update: 24B/8B Modell-Tests, :wiki-Befehl, wiki-Doku, Modell-Vergleich ... - MODELS.md: 8B vs 24B Vergleich, :wiki-Doku, Entscheidungsbaum - README.md: 24B mit ⚠️ Manuell markiert (FILE:-Pattern unzuverlässig) - SESSION_HANDOVER.md: Neue Session 14:30-18:00 - TEST_SCENARIO.md: Referenz-Testszenario - crowdcode.js: 24B-Kompatibilität (flexible FILE:-Erkennung, :wiki-Befehl, configurable Timeout/GPU/Context via ENV, Streaming AbortController, Orphan-Codeblock-Detection)	2026-07-10 09:42:29 +02:00
xray	1cfaaf4e22	initial: MiniLlama — portable LLM chat for USB stick (Windows + Linux) ... llama.cpp b9936 binaries for x86_64 (Linux Ubuntu + Windows CPU) Dynamic model selection from models/ dir GGUF models: Gemma-4-E2B, Qwen2.5-1.5B, Qwen3.5-4B Cross-platform start.sh / start.bat scripts Deploy script for USB stick export	2026-07-09 10:00:25 +02:00