Update app.py

app.py

@@ -17,6 +17,7 @@ import gradio as gr
 HF_REPO = "bartleby-Qwen3-4B-Instruct-2507-gguf"
 HF_FILE = "bartleby-qwen3-4b-lora.Q4_K_M.gguf"
 
+
 # ----------------------------
 # llama.cpp server settings
 # ----------------------------
@@ -25,7 +26,7 @@ PORT = 8080
 BASE_URL = f"http://{HOST}:{PORT}"
 
 # Keep context sane for CPU Spaces
-CTX_SIZE = 4096
+CTX_SIZE = 1024
 
 SYSTEM_PROMPT = ""
 # Threads: Spaces CPU Basic is typically 2 vCPU