Cambiamos por un modelo mas pequeño.

app.py

@@ -36,7 +36,7 @@ def initLLM():
         * HuggingFaceH4/zephyr-7b-beta
     """
 
-    model_path = hf_hub_download(repo_id="bartowski/Llama-3.2-1B-Instruct-GGUF", filename="Llama-3.2-1B-Instruct-Q5_K_S.gguf")
+    model_path = hf_hub_download(repo_id="bartowski/Llama-3.2-1B-Instruct-GGUF", filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf")
 
     llm = ChatLlamaCpp(
         model_path=model_path,