diff --git a/crates/llama-cpp-bindings/src/engine.cc b/crates/llama-cpp-bindings/src/engine.cc
index 2aeedab..0b335ae 100644
--- a/crates/llama-cpp-bindings/src/engine.cc
+++ b/crates/llama-cpp-bindings/src/engine.cc
@@ -123,7 +123,6 @@ std::unique_ptr<TextInferenceEngine> create_engine(rust::Str model_path) {
   llama_model* model = llama_load_model_from_file(std::string(model_path).c_str(), model_params);
 
   if (!model) {
-    fprintf(stderr , "%s: error: unable to load model\n" , __func__);
     return nullptr;
   }
 
diff --git a/crates/llama-cpp-bindings/src/lib.rs b/crates/llama-cpp-bindings/src/lib.rs
index da91aa2..af26ede 100644
--- a/crates/llama-cpp-bindings/src/lib.rs
+++ b/crates/llama-cpp-bindings/src/lib.rs
@@ -42,8 +42,12 @@ pub struct LlamaEngine {
 
 impl LlamaEngine {
     pub fn create(options: LlamaEngineOptions) -> Self {
+        let engine = create_engine(&options.model_path);
+        if engine.is_null() {
+            panic!("Unable to load model: {}", options.model_path);
+        }
         LlamaEngine {
-            engine: Mutex::new(create_engine(&options.model_path)),
+            engine: Mutex::new(engine),
             tokenizer: Arc::new(Tokenizer::from_file(&options.tokenizer_path).unwrap()),
             decoding_factory: DecodingFactory::default(),
         }