diff --git a/llama_stack/cli/stack/run.py b/llama_stack/cli/stack/run.py
index 73536491b..0c9c74518 100644
--- a/llama_stack/cli/stack/run.py
+++ b/llama_stack/cli/stack/run.py
@@ -178,6 +178,12 @@ class StackRun(Subcommand):
             # else must be venv since that is the only valid option left.
             current_venv = os.environ.get("VIRTUAL_ENV")
             venv = args.image_name or current_venv
+            if not venv:
+                cprint(
+                    "No current virtual environment detected, please specify a virtual environment name with --image-name",
+                    color="red",
+                )
+                return
             script = importlib.resources.files("llama_stack") / "distribution/start_venv.sh"
             run_args = [
                 script,
@@ -206,5 +212,4 @@ class StackRun(Subcommand):
 
         if args.tls_keyfile and args.tls_certfile:
             run_args.extend(["--tls-keyfile", args.tls_keyfile, "--tls-certfile", args.tls_certfile])
-
         run_with_pty(run_args)
diff --git a/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py b/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
index 6a83836e6..bfb09af53 100644
--- a/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
+++ b/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
@@ -44,7 +44,6 @@ class SentenceTransformersInferenceImpl(
         pass
 
     async def register_model(self, model: Model) -> None:
-        _ = self._load_sentence_transformer_model(model.provider_resource_id)
         return model
 
     async def unregister_model(self, model_id: str) -> None: