Update app.py

app.py

@@ -5,7 +5,7 @@ import os
 # Determine the number of CPU cores available
 num_cores = os.cpu_count()
 # Use 75% of available cores, but at least 4
-threads = max(3, int(num_cores * 0.75))
+threads = max(4, int(num_cores * 0.75))
 
 llm = Llama(model_path="model.gguf", n_ctx=3072, n_threads=threads, chat_format="chatml")