diff --git a/invokeai/backend/model_manager/load/model_loaders/flux.py b/invokeai/backend/model_manager/load/model_loaders/flux.py
index 40c77f5982..79613b7602 100644
--- a/invokeai/backend/model_manager/load/model_loaders/flux.py
+++ b/invokeai/backend/model_manager/load/model_loaders/flux.py
@@ -90,9 +90,9 @@ class ClipCheckpointModel(ModelLoader):
 
         match submodel_type:
             case SubModelType.Tokenizer:
-                return CLIPTokenizer.from_pretrained(config.path)
+                return CLIPTokenizer.from_pretrained(Path(config.path) / "tokenizer")
             case SubModelType.TextEncoder:
-                return CLIPTextModel.from_pretrained(config.path)
+                return CLIPTextModel.from_pretrained(Path(config.path) / "text_encoder")
 
         raise ValueError(
             f"Only Tokenizer and TextEncoder submodels are currently supported. Received: {submodel_type.value if submodel_type else 'None'}"
diff --git a/invokeai/backend/model_manager/starter_models.py b/invokeai/backend/model_manager/starter_models.py
index 69b9c1bd27..d08fc9fc97 100644
--- a/invokeai/backend/model_manager/starter_models.py
+++ b/invokeai/backend/model_manager/starter_models.py
@@ -72,8 +72,8 @@ t5_8b_quantized_encoder = StarterModel(
 clip_l_encoder = StarterModel(
     name="clip-vit-large-patch14",
     base=BaseModelType.Any,
-    source="openai/clip-vit-large-patch14",
-    description="CLIP-L text encoder (used in FLUX pipelines). ~3GB",
+    source="InvokeAI/clip-vit-large-patch14-text-encoder::bfloat16",
+    description="CLIP-L text encoder (used in FLUX pipelines). ~250MB",
     type=ModelType.CLIPEmbed,
 )