diff --git a/packages/tasks/src/tasks/image-text-to-text/data.ts b/packages/tasks/src/tasks/image-text-to-text/data.ts
index 41084651d..e26de6551 100644
--- a/packages/tasks/src/tasks/image-text-to-text/data.ts
+++ b/packages/tasks/src/tasks/image-text-to-text/data.ts
@@ -87,7 +87,7 @@ const taskData: TaskDataCustom = {
 	],
 	summary:
 		"Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.",
-	widgetModels: ["microsoft/kosmos-2-patch14-224"],
+	widgetModels: ["meta-llama/Llama-3.2-11B-Vision-Instruct"],
 	youtubeId: "IoGaGfU1CIg",
 };