diff --git a/router/router.py b/router/router.py
index 7fe2f31..53d7b64 100644
--- a/router/router.py
+++ b/router/router.py
@@ -19,7 +19,7 @@ GPU_URLS = {
 }
 # Max concurrent requests per GPU (based on llama.cpp --parallel)
 GPU_MAX_CONCURRENT = {
-    "qwen3.6-35B-A3B": 2,   # 2 slots (Dense-first routing reduces thermal load)
+    "qwen3.6-35B-A3B": 1,   # 1 slot (95C thermal emergency)
     "qwen3.6-27B-code": 2,  # 2 slots (128K context frees VRAM)
     "qwen3.5-9b-vlm": 2,       # 2 slots (12GB VRAM, 4GB headroom)
 }