diff --git a/apps/www/_blog/2023-07-13-pgvector-performance.mdx b/apps/www/_blog/2023-07-13-pgvector-performance.mdx
index dea6e8fc316..688764ce8ab 100644
--- a/apps/www/_blog/2023-07-13-pgvector-performance.mdx
+++ b/apps/www/_blog/2023-07-13-pgvector-performance.mdx
@@ -154,6 +154,19 @@ Again, it is NOT our goal to prove that pgvector is better than Qdrant for runni
 
 </div>
 
+<div>
+  <img
+    alt="multi database"
+    className="dark:hidden"
+    src="/images/blog/2023-07-13-pgvector-performance/pgvector-8xl--light.png"
+  />
+  <img
+    alt="multi database"
+    className="hidden dark:block"
+    src="/images/blog/2023-07-13-pgvector-performance/pgvector-8xl--dark.png"
+  />
+</div>
+
 Although more compute is required to match Qdrant's precision and RPS levels concurrently, this is still a satisfying outcome. It means that it's not a _necessity_ to use another vector database - if you want to lower your operational complexity, just increase your Postgres size.
 
 ### Final results: pgvector performance