Update app.py

app.py

@@ -12,12 +12,12 @@ import ollama
 
 # Model from run.sh
 AVAILABLE_MODELS = [
-    'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     'hf.co/bartowski/Qwen_Qwen3-1.7B-GGUF:Q5_K_M',
     'hf.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF:Q4_K_M',
-    'hf.co/bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF:Q4_K_M',
+    #'hf.co/bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF:Q4_K_M',
+    'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     'smollm2:360m-instruct-q5_K_M',
-    'hf.co/unsloth/gemma-3-4b-it-qat-GGUF:Q4_K_M', #Slow.
+    #'hf.co/unsloth/gemma-3-4b-it-qat-GGUF:Q4_K_M', #Slow.
     'gemma3n:e2b-it-q4_K_M',
     'granite3.3:2b',
     'hf.co/bartowski/tencent_Hunyuan-4B-Instruct-GGUF:Q4_K_M'