diff --git a/ops/node2_model_capabilities.yml b/ops/node2_model_capabilities.yml
new file mode 100644
index 00000000..ae88fee6
--- /dev/null
+++ b/ops/node2_model_capabilities.yml
@@ -0,0 +1,270 @@
+# NODA2 Model Capabilities — Machine-readable
+# Node: MacBook Pro M4 Max, 64GB unified memory
+# Date: 2026-02-27
+# Usage: router offload decisions, swapper config, capability queries
+
+node_id: noda2
+hostname: MacBook-Pro.local
+hardware:
+  cpu: "Apple M4 Max"
+  ram_gb: 64
+  unified_memory: true
+  gpu: "Apple Silicon (MPS/Metal)"
+
+# ─── LLM HEAVY ────────────────────────────────────────────────────────────────
+llm_heavy:
+  - name: qwen3.5:35b-a3b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 9.3
+    params: "14.8B MoE"
+    quality: high
+    speed: fast_for_size
+    recommended: true
+    note: "Primary reasoning model. MoE architecture — fast despite 14.8B active params."
+
+  - name: glm-4.7-flash:32k
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 19.0
+    params: "~32B"
+    quality: high
+    speed: medium
+    recommended: false
+    note: "Duplicate of q4_K_M variant. Keep only one."
+
+  - name: deepseek-r1:70b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 42.0
+    params: "70B"
+    quality: very_high
+    speed: slow
+    recommended: false
+    note: "Rarely needed. Only for max-quality reasoning tasks."
+
+  - name: Qwen3.5-35B-A3B-Q4_K_M.gguf
+    backend: llama-server
+    base_url: http://localhost:11435
+    size_gb: 20.0
+    params: "34.6B"
+    quality: high
+    speed: fast
+    recommended: false
+    note: "DUPLICATE of qwen3.5:35b-a3b in Ollama. Same model, different backend. Remove or unify."
+
+# ─── LLM SMALL/MEDIUM ─────────────────────────────────────────────────────────
+llm_small:
+  - name: qwen3:14b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 9.3
+    params: "14B"
+    quality: medium_high
+    speed: fast
+    note: "Good all-rounder. Used by swapper as default."
+
+  - name: gemma3:latest
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 3.3
+    params: "4B"
+    quality: medium
+    speed: very_fast
+    recommended: true
+    note: "Best small model for routing, classification, quick Q&A."
+
+  - name: phi3:latest
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 2.2
+    params: "3.8B"
+    quality: medium
+    speed: very_fast
+    note: "Lightweight general model. Can replace with gemma3."
+
+  - name: gpt-oss:latest
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 13.0
+    params: "20.9B"
+    quality: medium_high
+    speed: medium
+    note: "Old model. Not recommended for new workloads."
+
+  - name: mistral-nemo:12b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 7.1
+    params: "12B"
+    quality: medium
+    speed: medium
+    note: "Old. Not recommended for new workloads."
+
+# ─── CODE ─────────────────────────────────────────────────────────────────────
+code:
+  - name: deepseek-coder:33b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 18.0
+    params: "33B"
+    quality: high
+    speed: medium
+    note: "Good for code review. Heavy, cold-start slow."
+
+  - name: starcoder2:3b
+    backend: ollama
+    base_url: http://localhost:11434
+    size_gb: 1.7
+    params: "3B"
+    quality: medium
+    speed: very_fast
+    note: "Fast code completion. Limited context."
+
+# ─── VISION ───────────────────────────────────────────────────────────────────
+vision_fast:
+  - name: llava:13b
+    backend: ollama
+    base_url: http://localhost:11434
+    swapper_url: http://localhost:8890/vision
+    size_gb: 8.0
+    params: "13B"
+    quality: medium
+    speed: medium
+    installed: true
+    active_in_swapper: true
+    note: "P0 fallback. CLIP-based. Outdated architecture but functional."
+
+vision_hq:
+  - name: MiniCPM-V-4_5
+    backend: hf_transformers
+    size_gb: 16.0
+    params: "8B"
+    quality: high
+    speed: medium
+    installed: true
+    active_in_swapper: false
+    note: "RECOMMENDED for P2. Better than llava:13b. Needs integration into Swapper."
+
+  - name: Qwen3-VL-32B-Instruct
+    backend: hf
+    size_gb: 0
+    installed: false
+    note: "Only refs/ placeholder — NOT downloaded. Would require 65+ GB."
+
+# ─── EMBEDDING ────────────────────────────────────────────────────────────────
+embedding:
+  - name: sentence-transformers/all-MiniLM-L6-v2
+    backend: open-webui
+    size_gb: 0.1
+    installed: true
+    active: true
+    note: "Used by open-webui for RAG. Not exposed as standalone endpoint."
+
+  - name: TaylorAI/bge-micro-v2
+    backend: open-webui
+    size_gb: 0.05
+    installed: true
+    active: true
+    note: "Auxiliary embedding in open-webui."
+
+  - name: Qwen/Qwen2.5-7B-Instruct
+    backend: hf_transformers
+    size_gb: 14.0
+    installed: true
+    active: false
+    note: "HF weights only. Can be used for embedding but not configured."
+
+# ─── STT ──────────────────────────────────────────────────────────────────────
+stt:
+  - name: mlx-community/whisper-large-v3-turbo-asr-fp16
+    backend: mlx
+    size_gb: 1.5
+    device: mps_metal
+    quality: high
+    speed: fast
+    installed: true
+    active: false
+    note: "READY — installed, MLX-accelerated. NOT integrated into Swapper or memory-service. P2 task."
+
+  - name: whisper-base
+    backend: open-webui
+    size_gb: 0.15
+    device: cpu
+    quality: low
+    installed: true
+    active: true
+    note: "Active in open-webui only. Low quality."
+
+# ─── TTS ──────────────────────────────────────────────────────────────────────
+tts:
+  - name: mlx-community/Kokoro-82M-bf16
+    backend: mlx
+    size_gb: 0.35
+    device: mps_metal
+    quality: high
+    speed: fast
+    installed: true
+    active: false
+    note: "READY — installed, MLX-accelerated. NOT integrated into any service. P2 task."
+
+# ─── IMAGE GENERATION ─────────────────────────────────────────────────────────
+image_gen:
+  - name: flux2-dev-Q8_0.gguf
+    backend: comfyui
+    path: ~/ComfyUI/models/checkpoints/
+    size_gb: 33.0
+    quality: very_high
+    installed: true
+    active: false
+    note: "ComfyUI + llama.cpp GGUF format. FLUX.2-dev — state-of-art image gen."
+
+  - name: ltx-2-19b-distilled-fp8.safetensors
+    backend: comfyui
+    path: ~/Documents/ComfyUI/models/checkpoints/
+    size_gb: 25.0
+    type: video_gen
+    quality: very_high
+    installed: true
+    active: false
+    note: "LTX-2 19B — video generation. Very large."
+
+  - name: z_image_turbo_bf16.safetensors
+    backend: comfyui
+    size_gb: 11.0
+    quality: high
+    installed: true
+    active: false
+    note: "Fast image gen via ComfyUI."
+
+  - name: SDXL-base-1.0 + refiner
+    backend: comfyui_symlink
+    size_gb: 72.0
+    quality: medium
+    installed: true
+    active: false
+    note: "Legacy SDXL. Very large. Consider cleanup."
+
+  - name: sdxl_sofia_lora_v1.safetensors
+    backend: comfyui_lora
+    size_gb: 0.08
+    installed: true
+    active: false
+    note: "Custom Sofiia appearance LoRA for SDXL."
+
+# ─── OCR ──────────────────────────────────────────────────────────────────────
+ocr:
+  - name: "(none configured)"
+    note: "Swapper /ocr returns 405. No dedicated OCR model. Could use llava:13b or MiniCPM-V as OCR."
+
+# ─── ROUTING POLICY (suggestions) ────────────────────────────────────────────
+routing_policy:
+  nats_subjects:
+    vision_request: "node.noda2.vision.request"
+    vision_reply:   "node.noda2.vision.reply.*"
+    stt_request:    "node.noda2.stt.request"
+    llm_request:    "node.noda2.llm.request"
+  default_vision_model: "llava:13b"
+  recommended_vision_model: "MiniCPM-V-4_5 (needs integration)"
+  default_llm: "qwen3.5:35b-a3b"
+  default_small_llm: "gemma3:latest"
diff --git a/ops/node2_model_gaps.yml b/ops/node2_model_gaps.yml
new file mode 100644
index 00000000..39684bc5
--- /dev/null
+++ b/ops/node2_model_gaps.yml
@@ -0,0 +1,255 @@
+# NODA2 Model Gaps & Optimization Analysis
+# Date: 2026-02-27
+# Node: MacBook Pro M4 Max (NODA2)
+# Status: READ-ONLY analysis — no changes applied
+
+# ─── MODELS INSTALLED BUT UNUSED ─────────────────────────────────────────────
+models_installed_but_unused:
+  - id: GAP-01
+    model: "mlx-community/whisper-large-v3-turbo-asr-fp16"
+    size_gb: 1.5
+    installed: true
+    integrated: false
+    priority: P2
+    action: >
+      Integrate into memory-service or swapper as STT backend.
+      Uses MLX for Metal acceleration — fast on M4 Max.
+      Candidate: POST /transcribe endpoint in memory-service.
+
+  - id: GAP-02
+    model: "mlx-community/Kokoro-82M-bf16"
+    size_gb: 0.35
+    installed: true
+    integrated: false
+    priority: P2
+    action: >
+      Integrate as TTS backend. Kokoro via MLX is fast on Apple Silicon.
+      Candidate: POST /tts endpoint in memory-service or standalone service.
+
+  - id: GAP-03
+    model: "openbmb/MiniCPM-V-4_5"
+    size_gb: 16.0
+    installed: true
+    integrated: false
+    priority: P2
+    action: >
+      Better vision quality than llava:13b.
+      Option A: Serve via Ollama (needs GGUF conversion or mlx-lm).
+      Option B: Direct HF inference via memory-service endpoint.
+      Option C: Dedicated FastAPI microservice on port 8893.
+
+  - id: GAP-04
+    model: "Qwen/Qwen2.5-7B-Instruct"
+    size_gb: 14.0
+    installed: true
+    integrated: false
+    priority: P3
+    action: >
+      HF weights sitting idle. If needed — convert to Ollama (modelfile)
+      or use via transformers. Otherwise candidate for cleanup.
+
+  - id: GAP-05
+    model: "Qwen/Qwen2.5-1.5B-Instruct"
+    size_gb: 2.9
+    installed: true
+    integrated: false
+    priority: P3
+    action: >
+      Very small model. Could serve as ultra-fast routing/classification
+      if converted to Ollama. Otherwise cleanup.
+
+  - id: GAP-06
+    model: "flux2-dev-Q8_0.gguf + ltx-2-19b + SDXL + FLUX.1-*"
+    size_gb_total: 141
+    installed: true
+    integrated: false
+    priority: P3
+    action: >
+      ComfyUI stack running but not exposed as API endpoint.
+      No REST API service for Sofiia to call image/video generation.
+      Would need a ComfyUI API wrapper (comfyui-api-proxy) to integrate.
+
+# ─── MODELS CONFIGURED BUT MISSING ───────────────────────────────────────────
+models_configured_but_missing:
+  - id: MISS-01
+    model: "gemma2:27b"
+    configured_in: swapper_config_node2.yaml
+    installed: false
+    priority: P2
+    action: >
+      Swapper references gemma2:27b but it's NOT in ollama list.
+      Either: ollama pull gemma2:27b (15GB) or remove from swapper config.
+      Recommend: remove (gemma3:latest is 3.3GB and more modern).
+
+  - id: MISS-02
+    model: "qwen2.5-coder:32b"
+    configured_in: swapper_config_node2.yaml
+    installed: false
+    priority: P2
+    action: >
+      Swapper references qwen2.5-coder:32b but NOT in ollama list.
+      Either: pull (19GB) or remove from config.
+      deepseek-coder:33b already covers this role.
+
+  - id: MISS-03
+    model: "gpt-oss:latest"
+    configured_in: swapper_config_node2.yaml
+    installed: true
+    priority: P3
+    note: "Available in Ollama. Old model, low usage."
+
+  - id: MISS-04
+    model: "Qwen3-VL-32B-Instruct"
+    configured_in: "NOT configured (only refs/ placeholder in HF cache)"
+    installed: false
+    priority: P3
+    note: "Only 4KB placeholder. Would need 65+ GB download to use."
+
+# ─── DUPLICATED MODELS ───────────────────────────────────────────────────────
+duplicated_models:
+  - id: DUP-01
+    model: "Qwen3.5-35B-A3B"
+    instances:
+      - backend: ollama
+        name: "qwen3.5:35b-a3b"
+        size_gb: 9.3
+        path: "~/.ollama/models/"
+      - backend: llama-server
+        name: "Qwen3.5-35B-A3B-Q4_K_M.gguf"
+        size_gb: 20.0
+        path: "~/Library/Application Support/llama.cpp/models/"
+    total_duplicate_gb: 29.3
+    priority: P1
+    action: >
+      Two instances of same model (different quant format, same weights).
+      Ollama uses optimized .gguf internally (~9.3GB).
+      llama-server uses separate 20GB .gguf file.
+      RECOMMEND: Stop llama-server process and delete the 20GB file.
+      Use ollama as single Qwen3.5 backend.
+      Saves: 20 GB disk, eliminates port confusion.
+
+  - id: DUP-02
+    model: "glm-4.7-flash"
+    instances:
+      - name: "glm-4.7-flash:32k"
+        size_gb: 19.0
+      - name: "glm-4.7-flash:q4_K_M"
+        size_gb: 19.0
+    total_duplicate_gb: 38.0
+    priority: P2
+    action: >
+      Two identical GLM-4.7-flash quants. Choose one (32k recommended
+      for longer context), remove the other. Saves 19 GB.
+
+# ─── GPU / MEMORY CONFLICTS ──────────────────────────────────────────────────
+gpu_conflicts:
+  - id: GPU-01
+    description: >
+      llama-server (port 11435) and Ollama (port 11434) both use
+      Metal/MPS for the SAME model (Qwen3.5-35B-A3B).
+      On Apple Silicon unified memory, this means both could load
+      model weights simultaneously → 20GB + 9.3GB = 29.3GB consumed
+      from 64GB unified memory without any active inference.
+    severity: medium
+    priority: P1
+    action: "Stop llama-server. Use only Ollama for this model."
+
+  - id: GPU-02
+    description: >
+      No single-model-in-VRAM policy on NODA2 (unlike NODA1).
+      Ollama can keep multiple models warm simultaneously.
+      On 64GB unified memory this is less critical than on NODA1's 20GB,
+      but for large models (deepseek-r1:70b = 42GB) concurrent loading
+      can cause swap pressure.
+    severity: low
+    priority: P3
+    action: >
+      Set OLLAMA_MAX_LOADED_MODELS=1 in Ollama env if strict policy needed.
+      Current 64GB RAM is usually sufficient for 1-2 medium models.
+
+# ─── MISALIGNED SWAPPER CONFIG ───────────────────────────────────────────────
+misaligned_swapper_config:
+  - id: SW-01
+    issue: "gemma2:27b referenced in swapper but not installed in Ollama"
+    severity: medium
+    priority: P2
+    fix: "Remove gemma2-27b entry from swapper_config_node2.yaml or install"
+
+  - id: SW-02
+    issue: "qwen2.5-coder:32b referenced in swapper but not installed"
+    severity: medium
+    priority: P2
+    fix: "Remove qwen2.5-coder-32b entry or install model"
+
+  - id: SW-03
+    issue: "ollama.url in swapper_config set to host.docker.internal:11434 (FIXED in P1)"
+    severity: resolved
+    note: "Fixed 2026-02-27"
+
+  - id: SW-04
+    issue: "STT/TTS sections are empty — whisper and kokoro installed but not configured"
+    severity: medium
+    priority: P2
+    fix: >
+      Add stt section pointing to mlx-community/whisper-large-v3-turbo-asr-fp16
+      Add tts section pointing to mlx-community/Kokoro-82M-bf16
+
+  - id: SW-05
+    issue: "No OCR model configured — /ocr returns 405"
+    severity: low
+    priority: P3
+    fix: "Either configure llava-13b as OCR fallback or integrate got-ocr2/granite-docling"
+
+# ─── REDUNDANT BACKENDS ──────────────────────────────────────────────────────
+redundant_backends:
+  - id: RED-01
+    description: "llama-server (port 11435) running alongside Ollama for identical model"
+    redundant: llama-server
+    preferred: ollama
+    priority: P1
+    action: "Kill llama-server process, delete 20GB .gguf file, update router profile to use port 11434"
+
+  - id: RED-02
+    description: "open-webui whisper-base (low quality) vs mlx whisper-large-v3-turbo (high quality, idle)"
+    redundant: open-webui whisper-base
+    preferred: mlx whisper-large-v3-turbo
+    priority: P2
+    action: "Integrate mlx whisper as service, configure open-webui to use external STT URL"
+
+# ─── RECOMMENDED CLEANUP ─────────────────────────────────────────────────────
+recommended_cleanup:
+  immediate_P1:
+    - action: "Stop llama-server process + delete ~/Library/Application Support/llama.cpp/models/Qwen3.5-35B-A3B-Q4_K_M.gguf"
+      savings_gb: 20
+      risk: low
+
+  next_sprint_P2:
+    - action: "Remove glm-4.7-flash:q4_K_M from Ollama (keep :32k)"
+      savings_gb: 19
+      risk: low
+    - action: "Remove gemma2-27b and qwen2.5-coder:32b from swapper_config_node2.yaml (not installed)"
+      savings_gb: 0
+      risk: none
+    - action: "Integrate whisper-large-v3-turbo-asr-fp16 as STT endpoint"
+      savings_gb: 0
+      risk: medium
+    - action: "Integrate Kokoro-82M-bf16 as TTS endpoint"
+      savings_gb: 0
+      risk: medium
+    - action: "Integrate MiniCPM-V-4_5 as vision endpoint (replace llava:13b)"
+      savings_gb: 0
+      risk: medium
+
+  optional_P3:
+    - action: "Clean old HF models: Qwen/Qwen2.5-7B-Instruct + Qwen2.5-1.5B if not needed"
+      savings_gb: 17
+      risk: low
+    - action: "Clean SDXL-base-1.0 from hf_models (72GB!) if ComfyUI FLUX covers use case"
+      savings_gb: 72
+      risk: low
+    - action: "Remove gpt-oss:latest and mistral-nemo:12b from Ollama (old, replaced by qwen3)"
+      savings_gb: 20
+      risk: low
+
+  total_potential_savings_gb: 149
+  immediate_savings_gb: 20
diff --git a/ops/node2_models_inventory_20260227.json b/ops/node2_models_inventory_20260227.json
new file mode 100644
index 00000000..f0ea440b
--- /dev/null
+++ b/ops/node2_models_inventory_20260227.json
@@ -0,0 +1,141 @@
+{
+  "node_id": "noda2",
+  "hostname": "MacBook-Pro.local",
+  "timestamp": "2026-02-27T10:00:00Z",
+  "hardware": {
+    "cpu": "Apple M4 Max",
+    "ram_gb": 64,
+    "unified_memory": true,
+    "storage_total_tb": 1.8,
+    "storage_free_gb": 634,
+    "os": "macOS 26.3 (Darwin arm64 25.3.0)"
+  },
+
+  "backends": [
+    {
+      "id": "ollama-main",
+      "type": "ollama",
+      "version": "0.17.1",
+      "port": 11434,
+      "base_url": "http://localhost:11434",
+      "gpu_mode": "Apple Silicon MPS/Metal (unified memory)",
+      "currently_loaded": null,
+      "models_count": 12,
+      "models": [
+        {"name": "qwen3.5:35b-a3b",   "type": "llm",       "size_gb": 9.3,  "params": "14.8B MoE", "running": false, "modified": "2026-02-26", "tags": ["reasoning", "primary"]},
+        {"name": "qwen3:14b",          "type": "llm",       "size_gb": 9.3,  "params": "14B",       "running": false, "modified": "2026-02-26", "tags": ["general"]},
+        {"name": "gemma3:latest",      "type": "llm",       "size_gb": 3.3,  "params": "4B",        "running": false, "modified": "2026-02-25", "tags": ["general", "fast"]},
+        {"name": "glm-4.7-flash:32k",  "type": "llm",       "size_gb": 19.0, "params": "~32B",      "running": false, "modified": "2026-02-09", "tags": ["long-context"]},
+        {"name": "glm-4.7-flash:q4_K_M","type": "llm",     "size_gb": 19.0, "params": "~32B",      "running": false, "modified": "2026-02-09", "tags": ["duplicate-of-32k"]},
+        {"name": "llava:13b",          "type": "vision",    "size_gb": 8.0,  "params": "13B",       "running": false, "modified": "2025-11-27", "tags": ["vision", "multimodal", "p0-fallback"], "vision_capable": true},
+        {"name": "mistral-nemo:12b",   "type": "llm",       "size_gb": 7.1,  "params": "12B",       "running": false, "modified": "2025-11-21", "tags": ["general", "old"]},
+        {"name": "deepseek-coder:33b", "type": "code",      "size_gb": 18.0, "params": "33B",       "running": false, "modified": "2025-11-21", "tags": ["code", "heavy"]},
+        {"name": "deepseek-r1:70b",    "type": "llm",       "size_gb": 42.0, "params": "70B",       "running": false, "modified": "2025-11-21", "tags": ["reasoning", "very-heavy"]},
+        {"name": "starcoder2:3b",      "type": "code",      "size_gb": 1.7,  "params": "3B",        "running": false, "modified": "2025-11-21", "tags": ["code", "small"]},
+        {"name": "phi3:latest",        "type": "llm",       "size_gb": 2.2,  "params": "3.8B",      "running": false, "modified": "2025-11-21", "tags": ["small", "fast"]},
+        {"name": "gpt-oss:latest",     "type": "llm",       "size_gb": 13.0, "params": "20.9B",     "running": false, "modified": "2025-11-21", "tags": ["general", "old"]}
+      ]
+    },
+    {
+      "id": "llama-server-cpu",
+      "type": "llama.cpp",
+      "port": 11435,
+      "base_url": "http://localhost:11435",
+      "gpu_mode": "Apple Silicon Metal (via llama.cpp)",
+      "model_file": "/Users/apple/Library/Application Support/llama.cpp/models/Qwen3.5-35B-A3B-Q4_K_M.gguf",
+      "model_name": "Qwen3.5-35B-A3B-Q4_K_M",
+      "size_gb": 20.0,
+      "currently_loaded": true,
+      "note": "DUPLICATE — same model as qwen3.5:35b-a3b in Ollama. Two instances of identical model consume 2x disk."
+    },
+    {
+      "id": "swapper-service",
+      "type": "swapper",
+      "port": 8890,
+      "base_url": "http://localhost:8890",
+      "status": "healthy",
+      "active_model": null,
+      "mode": "single-active",
+      "ollama_url": "http://host.docker.internal:11434",
+      "gpu_enabled": true,
+      "metal_acceleration": true,
+      "llm_models_configured": 9,
+      "vision_models_configured": 1,
+      "stt_models_configured": 0,
+      "tts_models_configured": 0,
+      "vision_models": [
+        {"name": "llava-13b", "ollama_model": "llava:13b", "size_gb": 8.0, "status": "unloaded"}
+      ]
+    },
+    {
+      "id": "open-webui",
+      "type": "open-webui",
+      "port": 8080,
+      "base_url": "http://localhost:8080",
+      "ollama_base_url": "http://host.docker.internal:11434",
+      "whisper_model": "base",
+      "whisper_device": "cpu",
+      "embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
+      "note": "Internal WebUI for Ollama. Has Whisper-base STT (CPU) built-in."
+    }
+  ],
+
+  "hf_cache_models": [
+    {"name": "mlx-community/whisper-large-v3-turbo-asr-fp16", "type": "stt",       "size_gb": 1.5,  "backend": "mlx",        "installed": true,  "active": false, "note": "MLX Whisper — ready to use, NOT integrated into Swapper"},
+    {"name": "mlx-community/Kokoro-82M-bf16",                  "type": "tts",       "size_gb": 0.35, "backend": "mlx",        "installed": true,  "active": false, "note": "Kokoro TTS — ready to use, NOT integrated"},
+    {"name": "openbmb/MiniCPM-V-4_5",                         "type": "vision",    "size_gb": 16.0, "backend": "hf",         "installed": true,  "active": false, "note": "MiniCPM-V 4.5 — high-quality vision model, NOT in Swapper"},
+    {"name": "Qwen/Qwen2.5-7B-Instruct",                      "type": "llm",       "size_gb": 14.0, "backend": "hf",         "installed": true,  "active": false, "note": "HF weights only — not serving"},
+    {"name": "Qwen/Qwen2.5-1.5B-Instruct",                    "type": "llm",       "size_gb": 2.9,  "backend": "hf",         "installed": true,  "active": false, "note": "HF weights only — not serving"},
+    {"name": "Qwen/Qwen3-VL-32B-Instruct",                    "type": "vision",    "size_gb": 0.004,"backend": "hf",         "installed": false, "active": false, "note": "Only refs/ directory — model NOT downloaded (4KB, just placeholder)"},
+    {"name": "Aquiles-ai/FLUX.2-dev",                         "type": "image_gen", "size_gb": 105,  "backend": "hf/comfyui", "installed": true,  "active": false, "note": "FLUX.2-dev (105GB) — VERY large, used by ComfyUI"},
+    {"name": "google/gemma-3-12b-it-qat-q4_0-unquantized",    "type": "llm",       "size_gb": 0.004,"backend": "hf",         "installed": false, "active": false, "note": "Only refs/ — NOT downloaded"}
+  ],
+
+  "comfyui_models": {
+    "location": "~/Documents/ComfyUI/models + ~/ComfyUI/models",
+    "total_size_gb": 101,
+    "checkpoints": [
+      {"name": "flux2-dev-Q8_0.gguf",               "size_gb": 33.0,  "type": "image_gen", "path": "~/ComfyUI/models/checkpoints/"},
+      {"name": "ltx-2-19b-distilled-fp8.safetensors","size_gb": 25.0,  "type": "video_gen", "path": "~/Documents/ComfyUI/models/checkpoints/"}
+    ],
+    "diffusion_models": [
+      {"name": "z_image_turbo_bf16.safetensors",    "size_gb": 11.0,  "type": "image_gen"}
+    ],
+    "loras": [
+      {"name": "ltx-2-19b-distilled-lora-384.safetensors", "size_gb": 7.1,  "type": "video_gen"},
+      {"name": "sdxl_sofia_lora_v1.safetensors",           "size_gb": 0.08, "type": "image_gen", "note": "Sofiia custom LoRA"},
+      {"name": "ip-adapter-faceid-plusv2_sdxl_lora.safetensors", "size_gb": 0.35, "type": "image_gen"},
+      {"name": "sdxl_agent_lora_smoke.safetensors",        "size_gb": 0.02, "type": "image_gen"}
+    ],
+    "hf_linked": [
+      {"name": "FLUX.1-dev",      "size_gb": 40, "location": "~/hf_models/FLUX.1-dev"},
+      {"name": "FLUX.1-schnell",  "size_gb": 12, "location": "~/hf_models/FLUX.1-schnell"},
+      {"name": "SDXL-base-1.0",   "size_gb": 72, "location": "~/hf_models/stabilityai_sdxl_base_1.0"}
+    ]
+  },
+
+  "docker_containers": [
+    {"name": "dagi-router-node2",         "status": "Up 13m (healthy)", "port": "127.0.0.1:9102→8000"},
+    {"name": "dagi-gateway-node2",        "status": "Up 19h (healthy)", "port": "0.0.0.0:9300"},
+    {"name": "swapper-service-node2",     "status": "Up 14m (healthy)", "port": "0.0.0.0:8890", "note": "P1: should be 127.0.0.1:8890 (not yet applied via --remove-orphans)"},
+    {"name": "dagi-memory-service-node2", "status": "Up 19h (healthy)", "port": "0.0.0.0:8000"},
+    {"name": "dagi-qdrant-node2",         "status": "Up 19h (healthy)", "port": "0.0.0.0:6333-6334"},
+    {"name": "dagi-postgres-node2",       "status": "Up 19h (healthy)", "port": "0.0.0.0:5433"},
+    {"name": "dagi-neo4j-node2",          "status": "Up 19h (healthy)", "port": "0.0.0.0:7474,7687"},
+    {"name": "dagi-nats-node2",           "status": "Up 2h",            "port": "0.0.0.0:4222,8222"},
+    {"name": "open-webui",                "status": "Up 19h (healthy)", "port": "0.0.0.0:8080"},
+    {"name": "dagi-postgres",             "status": "Up 19h (healthy)", "port": "0.0.0.0:5432"},
+    {"name": "dagi-redis",                "status": "Up 19h (healthy)", "port": "0.0.0.0:6379"},
+    {"name": "sofiia-console",            "status": "Up 13m",           "port": "127.0.0.1:8002"}
+  ],
+
+  "non_docker_processes": [
+    {"name": "ollama",         "port": 11434, "type": "native",      "model_serving": "all ollama models"},
+    {"name": "llama-server",   "port": 11435, "type": "llama.cpp",   "model": "Qwen3.5-35B-A3B-Q4_K_M.gguf", "note": "DUPLICATE — same model as in Ollama"},
+    {"name": "spacebot",       "port": 19898, "type": "telegram-bot","note": "Sofiia Telegram bot"},
+    {"name": "gitea",          "port": 3000,  "type": "git-server",  "note": "Self-hosted Git"},
+    {"name": "opencode",       "port": 3456,  "type": "ai-coding",   "note": "AI coding tool"},
+    {"name": "Pieces OS",      "port": 39300, "type": "ai-assistant","note": "Pieces OS — dev AI tools, not LLM serving"},
+    {"name": "memory-service", "port": 8000,  "type": "uvicorn",     "note": "Running outside Docker (dev mode)"}
+  ]
+}
diff --git a/ops/node2_models_inventory_20260227.md b/ops/node2_models_inventory_20260227.md
new file mode 100644
index 00000000..890459ad
--- /dev/null
+++ b/ops/node2_models_inventory_20260227.md
@@ -0,0 +1,188 @@
+# NODA2 Full Model Inventory
+**MacBook Pro M4 Max — 64GB unified memory**  
+**Date:** 2026-02-27  
+**Status:** Read-only audit, no changes applied
+
+---
+
+## Загальна статистика
+
+| Параметр | Значення |
+|----------|---------|
+| Всього моделей (унікальних) | **20+** |
+| Реально використовуються зараз | **3** (qwen3.5 via Ollama/llama-server, llava:13b via Swapper) |
+| Встановлені але невикористовувані | **12** (whisper, kokoro, MiniCPM-V, ComfyUI stack, FLUX, ...) |
+| Дублюються | **2** (Qwen3.5-35B in Ollama + llama-server; GLM-4.7-flash:32k + :q4_K_M) |
+| Налаштовані в swapper, але відсутні в Ollama | **2** (gemma2:27b, qwen2.5-coder:32b) |
+| Є VL/vision-capable | **3** (llava:13b active, MiniCPM-V-4_5 idle, Qwen3-VL-32B not downloaded) |
+| Можна перейти на single-model policy | **Частково** (64GB дозволяє тримати 1-2 великих моделі) |
+| Потенційна економія диска (cleanup) | **~149 GB** |
+| Негайна економія (P1 llama-server) | **~20 GB** |
+
+---
+
+## A. Система
+
+| Параметр | Значення |
+|----------|---------|
+| CPU | Apple M4 Max |
+| RAM | 64 GB unified |
+| OS | macOS 26.3 (Darwin arm64) |
+| Storage free | 634 GB |
+| Ollama | v0.17.1 |
+| Docker | 29.2.1 / Compose v5.0.2 |
+
+---
+
+## B. Backends (активні)
+
+| Backend | Port | Статус | Модель |
+|---------|------|--------|--------|
+| Ollama (native) | 11434 | ✅ Running | 12 моделей, жодна не завантажена |
+| llama-server (llama.cpp) | 11435 | ✅ Running | Qwen3.5-35B-A3B-Q4_K_M.gguf |
+| Swapper (Docker) | 8890 | ✅ Healthy | active_model=null |
+| open-webui (Docker) | 8080 | ✅ Healthy | Whisper-base (STT, CPU) |
+| memory-service (uvicorn) | 8000 | ✅ Running | — |
+| ComfyUI | — | ❌ Not running | — (offline) |
+
+---
+
+## C. Ollama Models (12 шт.)
+
+| Модель | Розмір | Тип | GPU | Swapper | Рекомендація |
+|--------|--------|-----|-----|---------|--------------|
+| qwen3.5:35b-a3b | 9.3 GB | LLM (MoE) | Metal | ✅ так | 🟢 PRIMARY |
+| qwen3:14b | 9.3 GB | LLM | Metal | ✅ так | 🟢 Keep |
+| gemma3:latest | 3.3 GB | LLM (small) | Metal | ❌ не | 🟢 Add to swapper |
+| glm-4.7-flash:32k | 19 GB | LLM | Metal | ✅ так | 🟡 Keep 1, remove other |
+| glm-4.7-flash:q4_K_M | 19 GB | LLM | Metal | ❌ не | 🔴 DUPLICATE → видалити |
+| **llava:13b** | 8.0 GB | **Vision** | Metal | ✅ так | 🟡 P0 fallback, замінити |
+| mistral-nemo:12b | 7.1 GB | LLM | Metal | ❌ не | 🔴 Old → видалити |
+| deepseek-coder:33b | 18 GB | Code | Metal | ✅ так | 🟡 Heavy, keep if needed |
+| deepseek-r1:70b | 42 GB | LLM | Metal | ✅ так | 🟡 Very heavy, on-demand |
+| starcoder2:3b | 1.7 GB | Code | Metal | ❌ не | 🟡 Keep for fast code |
+| phi3:latest | 2.2 GB | LLM | Metal | ✅ так | 🟡 Replace with gemma3 |
+| gpt-oss:latest | 13 GB | LLM | Metal | ✅ так | 🔴 Old → видалити |
+
+---
+
+## D. llama-server (Дублікат!)
+
+| Параметр | Значення |
+|----------|---------|
+| Процес | `llama-server -m .../Qwen3.5-35B-A3B-Q4_K_M.gguf --port 11435` |
+| Файл | `~/Library/Application Support/llama.cpp/models/Qwen3.5-35B-A3B-Q4_K_M.gguf` |
+| Розмір | **20 GB** |
+| Тип | Ідентична модель до `qwen3.5:35b-a3b` в Ollama |
+| Проблема | DUP-01: 20 GB дублювання + плутає `router-config.node2.yml` |
+| Рекомендація | 🔴 **P1: Зупинити + видалити файл. Savings: 20 GB** |
+
+---
+
+## E. Swapper (swapper_config_node2.yaml)
+
+| Параметр | Значення |
+|----------|---------|
+| Status | ✅ healthy |
+| active_model | null |
+| ollama.url | http://host.docker.internal:11434 ✅ (виправлено P1) |
+| GPU | Metal enabled |
+| LLM моделей | 9 (2 не встановлені в Ollama!) |
+| Vision моделей | 1 (llava-13b) ✅ після P0 |
+| STT моделей | 0 ❌ (whisper є, але не підключений) |
+| TTS моделей | 0 ❌ (kokoro є, але не підключений) |
+
+---
+
+## F. HuggingFace Cache — встановлені, але невикористовувані
+
+| Модель | Тип | Розмір | Стан | Пріоритет |
+|--------|-----|--------|------|-----------|
+| whisper-large-v3-turbo-asr-fp16 (MLX) | STT | 1.5 GB | ✅ Installed | P2 integrate |
+| Kokoro-82M-bf16 (MLX) | TTS | 0.35 GB | ✅ Installed | P2 integrate |
+| MiniCPM-V-4_5 | Vision | 16 GB | ✅ Installed | P2 integrate |
+| Qwen2.5-7B-Instruct | LLM | 14 GB | ✅ Installed | P3 cleanup |
+| Qwen2.5-1.5B-Instruct | LLM | 2.9 GB | ✅ Installed | P3 cleanup |
+| Qwen3-VL-32B-Instruct | Vision | 4 KB | ❌ Only refs | — |
+| Aquiles-ai/FLUX.2-dev | Image gen | 105 GB | ✅ Installed | P3 ComfyUI |
+
+---
+
+## G. ComfyUI Stack (offline, не інтегрований)
+
+| Модель | Тип | Розмір | Якість |
+|--------|-----|--------|--------|
+| flux2-dev-Q8_0.gguf | Image gen | 33 GB | Very high |
+| ltx-2-19b-distilled-fp8 | **Video gen** | 25 GB | Very high |
+| z_image_turbo_bf16 | Image gen | 11 GB | High |
+| SDXL-base-1.0 (hf_models) | Image gen | 72 GB | Medium (old) |
+| sdxl_sofia_lora_v1 | LoRA (image) | 0.08 GB | — |
+
+**Загальний розмір ComfyUI + linked:** ~200+ GB  
+**Інтеграція з платформою:** ❌ Немає REST API wrapper
+
+---
+
+## H. Gaps Summary
+
+### 🔴 P1 — Негайно
+| ID | Проблема | Дія |
+|----|----------|-----|
+| DUP-01 | llama-server дублює Ollama (20 GB) | Зупинити процес, видалити файл |
+
+### 🟡 P2 — Цього тижня
+| ID | Проблема | Дія |
+|----|----------|-----|
+| GAP-01 | whisper-large-v3-turbo встановлений, не інтегрований | Додати STT endpoint |
+| GAP-02 | Kokoro TTS встановлений, не інтегрований | Додати TTS endpoint |
+| GAP-03 | MiniCPM-V-4_5 встановлений, не інтегрований | Замінити llava:13b в swapper |
+| SW-01 | gemma2:27b в swapper config, не встановлений | Видалити з config |
+| SW-02 | qwen2.5-coder:32b в swapper config, не встановлений | Видалити з config |
+| DUP-02 | glm-4.7-flash два однакові варіанти (38 GB) | Залишити тільки :32k |
+
+### 🔵 P3 — Наступний спринт
+| ID | Проблема | Дія |
+|----|----------|-----|
+| GAP-04/05 | Qwen2.5 HF weights (17 GB) idle | Cleanup або конвертація |
+| RED-02 | open-webui whisper-base vs MLX whisper | Upgrade |
+| GAP-06 | ComfyUI не має API wrapper | Integrate або leave as manual |
+| — | SDXL-base-1.0 (72 GB) якщо не потрібно | Cleanup |
+
+---
+
+## I. Executive Summary (15 bullets)
+
+1. **12 моделей в Ollama** — жодна не завантажена зараз; hot-start за 2-5с при запиті
+2. **llama-server дублює Ollama** — 20 GB зайвого диску і плутання портів (11434 vs 11435) → P1 cleanup
+3. **Vision ВІДНОВЛЕНО (P0)** — `llava:13b` активна в Swapper, inference ~3.5s через GPU
+4. **MiniCPM-V-4_5 (16 GB) встановлений але не підключений** — значно краще llava:13b → P2 upgrade
+5. **Whisper-large-v3-turbo (MLX, 1.5 GB) готовий** — STT відсутній в стеку → P2 integrate
+6. **Kokoro TTS (MLX, 0.35 GB) готовий** — TTS відсутній в стеку → P2 integrate
+7. **2 моделі в swapper config але відсутні в Ollama** — gemma2:27b, qwen2.5-coder:32b → видалити з config
+8. **GLM-4.7-flash дублюється** — два варіанти одного 19GB моделі → 19 GB зайвого
+9. **ComfyUI stack (200+ GB)** — FLUX.2-dev + LTX-2 video + SDXL — offline, немає API; величезні можливості без інтеграції
+10. **open-webui** запущений з whisper-base (CPU, низька якість) + embeddings — декількі неузгодженості
+11. **STT та TTS в Swapper порожні** — обидва /stt/models і /tts/models повертають `[]`
+12. **Qwen3.5-35B-A3B є рекомендованою основною моделлю** — MoE, 9.3 GB, fast на M4 Max
+13. **gemma3:latest (3.3 GB) не в Swapper** — найкращий "small fast" кандидат для швидких задач
+14. **Single-model policy** — на 64GB RAM менш критична ніж на NODA1 (20GB), але все одно рекомендована для порядку
+15. **Потенційна економія диску: 149 GB** (20 GB негайно); без втрати можливостей
+
+---
+
+## Рекомендована мінімальна конфігурація (якщо йти на оптимізацію)
+
+```
+Primary LLM:    qwen3.5:35b-a3b (Ollama)         — 9.3 GB
+Small/fast LLM: gemma3:latest (Ollama)             — 3.3 GB
+Vision:         MiniCPM-V-4_5 (HF → integrate)    — 16 GB
+STT:            whisper-large-v3-turbo (MLX)       — 1.5 GB
+TTS:            Kokoro-82M-bf16 (MLX)              — 0.35 GB
+Code:           deepseek-coder:33b (on-demand)     — 18 GB
+Image gen:      flux2-dev via ComfyUI (manual)     — 33 GB
+Video gen:      ltx-2 via ComfyUI (manual)         — 25 GB
+─────────────────────────────────────────────────────────
+Total active: ~30 GB (primary use case, fits in 64 GB RAM)
+```
+
+Це покрило б: text, vision, STT, TTS, code — в одному ноуті, без NODA1.