quantizations

packages/tracker/meshnet_tracker/model_presets.json

@@ -107,6 +107,51 @@
       },
       "input_price_per_1k_tokens": 0.00012,
       "output_price_per_1k_tokens": 0.00076
+    },
+    "qwen3.6-27b": {
+      "layers_start": 0,
+      "layers_end": 63,
+      "hf_repo": "Qwen/Qwen3.6-27B",
+      "revision": "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9",
+      "aliases": [
+        "qwen3.6-27b",
+        "Qwen3.6-27B",
+        "Qwen/Qwen3.6-27B"
+      ],
+      "recommended": true,
+      "deployment_status": "recommended",
+      "price_per_1k_tokens": 0.0006,
+      "hf_aliases": [
+        "qwen/qwen3.6-27b"
+      ],
+      "hf_verified_match_note": "Pinned to the official Qwen/Qwen3.6-27B BF16 revision. Live comparable-provider pricing refreshes this fallback when available; the last verified rate is retained when the provider lookup is unavailable.",
+      "required_model_bytes": 55576522126,
+      "download_size_bytes": 55576522126,
+      "native_quantization": "bfloat16",
+      "canonical_audit_dtype": "bfloat16",
+      "canonical_audit_quantization": "bfloat16",
+      "bytes_per_layer": {
+        "bfloat16": 868383159,
+        "int8": 434191580,
+        "nf4": 217095790
+      },
+      "metadata": {
+        "architecture": "Qwen3.5 hybrid linear-attention transformer",
+        "total_parameters": "27B",
+        "num_layers": 64,
+        "context_length": 262144,
+        "native_quantization": "bfloat16",
+        "download_size_gb": 52,
+        "recommended_short_name": "qwen3.6-27b",
+        "text_only": true,
+        "recommended_engines": [
+          "Transformers",
+          "vLLM",
+          "SGLang"
+        ]
+      },
+      "input_price_per_1k_tokens": 0.0002,
+      "output_price_per_1k_tokens": 0.001
     }
   }
-}
+}