use gemma 3 1b

app.py

@@ -2,10 +2,10 @@ import re
 import gradio as gr
 from llama_cpp import Llama
 
-model = "NousResearch/Hermes-3-Llama-3.2-3B-GGUF"
+model = "ggml-org/gemma-3-1b-it-GGUF"
 llm = Llama.from_pretrained(
     repo_id=model,
-    filename="*Q6_K.gguf",
+    filename="gemma-3-1b-it-Q8_0.gguf",
     verbose=True,
     use_mmap=True,
     use_mlock=True,