Phase 4: OpenClaw agent setup + expanded model catalog

- Add OpenClaw launchd plist (gateway on port 8080)
- Update Llama-3.3-70B Modelfile: fix FROM path, add tool-calling TEMPLATE,
  set num_ctx 32768 (fits 70B in 64GB with safe headroom)
- Update Codestral-22B and Qwen3-32B Modelfiles
- Add Modelfiles for all models in ~/Models/LLM and ~/Models/MLX:
  EVA-LLaMA-3.33-70B, Midnight-Miqu-70B, QwQ-32B, Qwen3.5-35B,
  Qwen3-Coder-30B, Qwen3-Coder-Next, Qwen3-VL-30B, GLM-4.6V-Flash,
  DeepSeek-R1-8B, gemma-3-27b, and MLX variants
- Add import-local-models.sh helper script

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

homeai-llm/modelfiles/DeepSeek-R1-0528-Qwen3-8B-MLX-8bit/config.json

@@ -0,0 +1,43 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "rope_type": "yarn",
+        "factor": 4.0,
+        "original_max_position_embeddings": 32768,
+        "attn_factor": 0.8782488562869419
+    },
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}