Update app.py

app.py

@@ -16,12 +16,14 @@ import ollama
 #ollama pull hf.co/bartowski/Qwen_Qwen3-1.7B-GGUF:Q5_K_M
 #ollama pull hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M
 
+
+# Model from run.sh
 AVAILABLE_MODELS = [
-    'hf.co/unsloth/gemma-3-4b-it-qat-GGUF:Q4_K_M', # This is the model created by run.sh
-    'hf.co/Menlo/Jan-nano-128k-gguf:Q4_K_M',
-    'hf.co/bartowski/Qwen_Qwen3-4B-GGUF:Q4_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',
-    'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M'
+    'gemma3n:e2b-it-q4_K_M',
+    'granite3.3:2b'
 ]
 
 # Default System Prompt