llm-inference-multimodel: add Qwen2.5-14B shadow instance (port 8002, gated off — VRAM co-residency not yet confirmed)

- New llama-server-qwen systemd unit template, gated by llm_qwen_service_enabled (default false)
- Idempotent GGUF download task (bartowski Qwen2.5-14B-Instruct-Q5_K_M, stat-guarded)
- Launch flags per local-llm-64k-context-recommendation.md: ctx-size 65536, flash-attn, q8_0 KV cache, batch 2048/ubatch 512, jinja, parallel 1
- verify.yml only starts/verifies the qwen unit when llm_qwen_service_enabled=true
- README: documents live VRAM gate finding (nvidia-smi 2026-08-06: Phi-4+Mistral already ~16.6/24GB, ~7.5GB free -- insufficient for Qwen weights concurrently) and options
- Does NOT touch llama-server-aux (8000) or llama-server-toolcall (8001) service state

ansible/roles/llm-inference-multimodel/defaults/main.yml

@@ -62,6 +62,29 @@ llm_toolcall_chat_template_file: "{{ llm_models_dir }}/templates/mistral-small-t
 llm_toolcall_service_name: llama-server-toolcall
 llm_toolcall_model_id: mistral-small-24b-instruct-2501
 
+# --- Shadow instance (port 8002, Qwen2.5-14B-Instruct) -----------------------
+# Shadow-deployment candidate to eventually replace the toolcall (8001) slot
+# per /home/hermes/reports/local-llm-64k-context-recommendation.md. Runs
+# alongside 8000/8001 during validation — does NOT replace either.
+# GATE: VRAM co-residency NOT confirmed as of 2026-08-06 — see role README /
+# deployment report. Do not enable/start this service until that is resolved
+# (either free VRAM by stopping llama-server-toolcall for the shadow window,
+# or reduce ctx-size). llm_qwen_service_enabled defaults to false so a normal
+# playbook run will template the unit but NOT start it.
+llm_qwen_service_enabled: false
+llm_qwen_port: 8002
+llm_qwen_model_path: "{{ llm_models_dir }}/Qwen2.5-14B-Instruct-Q5_K_M.gguf"
+llm_qwen_model_url: "https://huggingface.co/bartowski/Qwen2.5-14B-Instruct-GGUF/resolve/main/Qwen2.5-14B-Instruct-Q5_K_M.gguf"
+llm_qwen_model_min_bytes: 9500000000   # guard threshold; complete file ~10.5GB
+llm_qwen_ctx_size: 65536
+llm_qwen_parallel: 1
+llm_qwen_gpu_layers: 99
+llm_qwen_batch_size: 2048
+llm_qwen_ubatch_size: 512
+llm_qwen_service_name: llama-server-qwen
+llm_qwen_model_id: qwen2.5-14b-instruct
+llm_qwen_expected_vram_gb: 16.5
+
 # --- Existing Gemma baseline (rollback target — never modified by this role) -
 # Populated by Phase 0 discovery (tasks/discover.yml) if not already known.
 # Set here only as a fallback name to search for; discovery is authoritative.