diff --git a/llama_stack/providers/remote/inference/nvidia/models.py b/llama_stack/providers/remote/inference/nvidia/models.py
index fa9944be1..4305f4c6f 100644
--- a/llama_stack/providers/remote/inference/nvidia/models.py
+++ b/llama_stack/providers/remote/inference/nvidia/models.py
@@ -52,7 +52,7 @@ _MODEL_ENTRIES = [
         provider_model_id="baai/bge-m3",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dimensions": 1024,
+            "embedding_dimension": 1024,
             "context_length": 8192,
         },
     ),
diff --git a/llama_stack/templates/nvidia/run.yaml b/llama_stack/templates/nvidia/run.yaml
index 891fd112a..4c38ec24e 100644
--- a/llama_stack/templates/nvidia/run.yaml
+++ b/llama_stack/templates/nvidia/run.yaml
@@ -136,7 +136,7 @@ models:
   provider_model_id: meta/llama-3.2-90b-vision-instruct
   model_type: llm
 - metadata:
-    embedding_dimensions: 1024
+    embedding_dimension: 1024
     context_length: 8192
   model_id: baai/bge-m3
   provider_id: nvidia