Refactor LLM configuration to remove llamacpp support

- Removed references to llamacpp from configuration files, scripts, and documentation, streamlining the LLM setup process to focus solely on Ollama.
- Updated environment variables and paths to eliminate llamacpp-related entries, ensuring clarity in the configuration.
- Adjusted CLI commands and help messages to reflect the removal of llamacpp, enhancing user experience and reducing confusion.
- Revised documentation to provide clear guidance on using Ollama exclusively, including updates to setup instructions and runtime options.

ollama-models.example.yaml

@@ -1,17 +1,15 @@
 # Copy to ollama-models.yaml (gitignored). Used when LLM_RUNTIME=ollama.
-# name = exact tag for `ollama pull`. Empty models: [] → runtime only, no pull.
-# Purpose: SwarmUI prompt help + vision (RU/EN, low refusal).
+# name = exact tag for `ollama pull` (Ollama library / community).
+# Empty models: [] → runtime only, no pull.
+# Purpose: SwarmUI prompt help — vision + RU/EN on the same GPU as diffusion.
 
 models:
-  # Recommended: vision + Russian/English, ~6GB, abliterated
+  # Recommended (~6GB): vision + Russian/English, low refusal
   - name: huihui_ai/qwen2.5-vl-abliterated:7b
     default: true
 
-  # Lighter vision:
-  # - name: huihui_ai/qwen2.5-vl-abliterated:3b
-
-  # Text-only abliterate (~5GB):
-  # - name: huihui_ai/qwen2.5-abliterate:7b
-
-  # Official stock (more refusals):
-  # - name: qwen2.5:7b
+  # Alternatives (uncomment / use presets on setup|up):
+  # light  — huihui_ai/qwen2.5-vl-abliterated:3b   (~3GB)
+  # stock  — qwen2.5vl:7b                          (official library)
+  # text   — huihui_ai/qwen2.5-abliterate:7b       (no vision, ~5GB)
+  # big    — qwen2.5vl:32b                         (~21GB; llm-only)