feat: Jinja template thinking toggle, Qwen3.5-9B GGUF Q8_0

- Thinking/Instruct toggle via Jinja template patching in llama-cpp
  backend: creates separate handlers for thinking-enabled and
  thinking-disabled modes
- Replace lovedheart/Qwen3.5-9B-FP8 (safetensors, 15.8GB OOM) with
  unsloth/Qwen3.5-9B-GGUF Q8_0 (9.2GB, fits)
- Enable flash_attn in llama-cpp for better performance
- GGUF path resolution falls back to flat gguf/ directory

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

kischdle/llmux/config/models.yaml

@@ -1,10 +1,11 @@
 physical_models:
   qwen3.5-9b-fp8:
     type: llm
-    backend: transformers
-    model_id: "lovedheart/Qwen3.5-9B-FP8"
-    estimated_vram_gb: 9
-    supports_vision: true
+    backend: llamacpp
+    model_id: "unsloth/Qwen3.5-9B-GGUF"
+    model_file: "Qwen3.5-9B-Q8_0.gguf"
+    estimated_vram_gb: 10
+    supports_vision: false
     supports_tools: true
 
   qwen3.5-9b-fp8-uncensored: