Reduce threads to 2 (match HF free vCPUs), bump timeout to 300s

app.py

@@ -25,7 +25,7 @@ app.add_middleware(
 
 MODEL_PATH = os.environ.get("MODEL_PATH", "/app/models/locate-anything-q4_k.gguf")
 INFERENCE_MODE = os.environ.get("INFERENCE_MODE", "hybrid")
-N_THREADS = os.environ.get("N_THREADS", "4")
+N_THREADS = os.environ.get("N_THREADS", "2")
 
 _available = Path(MODEL_PATH).exists()
 
@@ -91,7 +91,7 @@ async def detect(
             ],
             capture_output=True,
             text=True,
-            timeout=120,
+            timeout=300,
         )
         elapsed = time.time() - t0