feat: compare safetensors and gguf on cpu and gpu

.scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json

@@ -5,7 +5,8 @@
         1,
         4
       ],
-      "id": "transformers-safetensors",
+      "device": "cpu",
+      "id": "transformers-safetensors-cpu",
       "recipe": "current safetensors recipe",
       "runtime": "transformers"
     },
@@ -14,7 +15,28 @@
         1,
         4
       ],
-      "id": "llama-cpp-gguf",
+      "device": "cpu",
+      "id": "llama-cpp-gguf-cpu",
+      "recipe": "whole-model GGUF recipe",
+      "runtime": "llama.cpp"
+    },
+    {
+      "concurrency_levels": [
+        1,
+        4
+      ],
+      "device": "gpu",
+      "id": "transformers-safetensors-gpu",
+      "recipe": "current safetensors recipe",
+      "runtime": "transformers"
+    },
+    {
+      "concurrency_levels": [
+        1,
+        4
+      ],
+      "device": "gpu",
+      "id": "llama-cpp-gguf-gpu",
       "recipe": "whole-model GGUF recipe",
       "runtime": "llama.cpp"
     }
@@ -34,11 +56,13 @@
   ],
   "model_target": {
     "architecture": "deepseek2",
+    "comparison_policy": "same model/revision, closest practical low-footprint precision pair: BF16 safetensors versus Q2_K GGUF",
     "gguf_quant": "Q2_K",
     "gguf_repo": "second-state/DeepSeek-V2-Lite-Chat-GGUF",
     "gguf_size_gb": 6.43,
     "name": "DeepSeek-V2-Lite-Chat",
     "rationale": "Smallest DeepSeek-family benchmark anchor that still points toward DeepSeek-V4-Flash; keeps the runtime on the DeepSeek2 path instead of falling back to a tiny but architecture-mismatched smoke model.",
+    "safetensors_precision": "bfloat16",
     "safetensors_repo": "deepseek-ai/DeepSeek-V2-Lite-Chat"
   },
   "notes": [