Update app.py

app.py

@@ -13,7 +13,8 @@ import ollama
 # Model from run.sh
 AVAILABLE_MODELS = [
     'smollm2:360m-instruct-q5_K_M',
-    'hf.co/unsloth/LFM2-1.2B-GGUF:Q5_K_M',
+    'hf.co/ggml-org/SmolLM3-3B-GGUF:Q4_K_M,
+    'hf.co/bartowski/nvidia_OpenReasoning-Nemotron-1.5B-GGUF:Q5_K_M,
     'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     'hf.co/unsloth/gemma-3-4b-it-qat-GGUF:Q4_K_M', #Slow.
     'hf.co/bartowski/Qwen_Qwen3-1.7B-GGUF:Q5_K_M',
@@ -34,7 +35,7 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutra
     with gr.Row():
         selected_model = gr.Radio(
             choices=AVAILABLE_MODELS,
-            value=AVAILABLE_MODELS[1], # Default to the first model in the list
+            value=AVAILABLE_MODELS[0], # Default to the first model in the list
             label="Select Model",
             info="Choose the LLM model to chat with.",
             interactive=True