diff --git a/llama_stack/providers/inline/inference/meta_reference/inference.py b/llama_stack/providers/inline/inference/meta_reference/inference.py
index 6743ca822..07fd4af44 100644
--- a/llama_stack/providers/inline/inference/meta_reference/inference.py
+++ b/llama_stack/providers/inline/inference/meta_reference/inference.py
@@ -36,8 +36,6 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP
     def __init__(self, config: MetaReferenceInferenceConfig) -> None:
         self.config = config
         model = resolve_model(config.model)
-        if model is None:
-            raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`")
         ModelRegistryHelper.__init__(
             self,
             [
@@ -47,6 +45,8 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP
                 )
             ],
         )
+        if model is None:
+            raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`")
         self.model = model
         # verify that the checkpoint actually is for this model lol
 
diff --git a/llama_stack/templates/meta-reference-gpu/meta_reference.py b/llama_stack/templates/meta-reference-gpu/meta_reference.py
index 2408ef972..f254bc920 100644
--- a/llama_stack/templates/meta-reference-gpu/meta_reference.py
+++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py
@@ -81,7 +81,7 @@ def get_distribution_template() -> DistributionTemplate:
                 "Port for the Llama Stack distribution server",
             ),
             "INFERENCE_MODEL": (
-                "meta-llama/Llama3.2-3B-Instruct",
+                "meta-llama/Llama-3.2-3B-Instruct",
                 "Inference model loaded into the Meta Reference server",
             ),
             "INFERENCE_CHECKPOINT_DIR": (