v5 Phase 1: Erklaeren (Swapping/RAM, Kontext, Guides-Neubau)

- Swapping-Klartext + Spitzenbedarf (peak_ram) pro Modell: Modelle-Konfig + Cookbook-Setup-Modal
  zeigen 'nur ein Modell gleichzeitig, groesstes zaehlt'. models.py: peak_ram_gb/_optimal in Meta.
- Kontextfenster: infoDot(ⓘ)-Helfer in ui.js + Tooltips an ctx-Feldern.
- Guides-Tab komplett neu = echter Anfaenger-Guide (LLM/GGUF/Quant/Kontext/Swapping/MCP/Skills/Agenten).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

routers/models.py

@@ -16,7 +16,7 @@ from auth import auth
 from config import CMD_TEMPLATE, CONFIG_PATH, DEFAULT_TTL, LLAMA_SWAP_URL, MODELS_DIR, TOKEN
 from jobengine import JOBS, start_job
 from llamaswap import _swap_get, read_config, write_config
-from hw_math import extract_params_b, max_ctx_for
+from hw_math import extract_params_b, max_ctx_for, estimate_memory_gb
 import re
 import os
 import psutil
@@ -101,8 +101,10 @@ def status():
                 "quant": quant,
                 "caps": caps,
                 "filename": filename,
-                "params_b": extract_params_b(filename or name),
-                "optimal_ctx": (max_ctx_for(extract_params_b(filename or name), quant or "Q4_K_M", ram_gb) if ram_gb else None),
+                "params_b": (_pb := extract_params_b(filename or name)),
+                "optimal_ctx": (_oc := (max_ctx_for(_pb, quant or "Q4_K_M", ram_gb) if ram_gb else None)),
+                "peak_ram_gb": round(estimate_memory_gb(_pb, quant or "Q4_K_M", ctx), 1),
+                "peak_ram_optimal_gb": (round(estimate_memory_gb(_pb, quant or "Q4_K_M", _oc), 1) if _oc else None),
             }
         }
     swap_ok = True