Update app.py

app.py

@@ -26,10 +26,6 @@ MODELS = [
         "url": "https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GGUF/resolve/main/qwen2.5-3b-instruct-q4_k_m.gguf",
         "name": "qwen2.5-3b-instruct"
     },
-    {
-        "url": "https://huggingface.co/Novaciano/Llama-3.2_1b_Uncensored_RP_Aesir_GGUF/resolve/main/Llama-3.2_1b_Uncensored_RP_Aesir.gguf",
-        "name": "llama-3.2-1b-rp"
-    },
     {
         "url": "https://huggingface.co/PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA_final-Q4_K_M-GGUF/resolve/main/unsloth.Q4_K_M.gguf",
         "name": "llama-3.2-3b-instruct-uncensored-lora"
@@ -67,7 +63,7 @@ class LLMManager:
                 llm_instance = Llama(
                     model_path=temp_path,
                     n_ctx=MAX_CONTEXT_TOKENS,
-                    n_batch=256,
+                    n_batch=512,
                     n_threads=2,
                     n_threads_batch=2,
                     use_mlock=True,