feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

Replace MTP with draft-dflash and a separate DFlash2 drafter GGUF.
Remove the qwen-classifier backend to free VRAM (GPU was at 100%).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

.env.example

@@ -6,8 +6,8 @@ LLAMA_GPU_LAYERS=999
 LLAMA_CTX_SIZE=262144
 LLAMA_PARALLEL=2
 
-# see docs/architecture.md#qwen-classifier
-LLAMA_CLASSIFIER_MODEL_FILE=Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf
+LLAMA_DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-Q4_K_M.gguf
+LLAMA_SPEC_N_MAX=7
 
 # --- SearXNG web search --- see docs/gateway.md#web-search
 # Auto-filled by update.sh — leave blank.