diff --git a/qdrant-landing/content/course/multi-vector-search/module-3/_index.md b/qdrant-landing/content/course/multi-vector-search/module-3/_index.md
index c6ce1f307..74dda6964 100644
--- a/qdrant-landing/content/course/multi-vector-search/module-3/_index.md
+++ b/qdrant-landing/content/course/multi-vector-search/module-3/_index.md
@@ -15,11 +15,10 @@ Tackle the memory and performance challenges of production-scale multi-vector se
 
 ## Today's path
 
-1. Memory Usage Implications and Solutions
+1. Multi-Stage Retrieval with Universal Query API
 2. Vector Quantization Techniques
 3. Pooling Techniques
 4. MUVERA
-5. Multi-Stage Retrieval with Universal Query API
-6. Evaluating Search Pipelines
+5. Evaluating Search Pipelines
 
 You'll master the optimization strategies needed to deploy multi-vector search at scale.
diff --git a/qdrant-landing/content/course/multi-vector-search/module-3/evaluating-pipelines.md b/qdrant-landing/content/course/multi-vector-search/module-3/evaluating-pipelines.md
index 0ef7f0598..ee8c63def 100644
--- a/qdrant-landing/content/course/multi-vector-search/module-3/evaluating-pipelines.md
+++ b/qdrant-landing/content/course/multi-vector-search/module-3/evaluating-pipelines.md
@@ -1,7 +1,7 @@
 ---
 title: "Evaluating Search Pipelines"
 description: Learn how to evaluate different search configurations in terms of cost, latency, and retrieval quality.
-weight: 6
+weight: 5
 ---
 
 {{< date >}} Module 3 {{< /date >}}
diff --git a/qdrant-landing/content/course/multi-vector-search/module-3/memory-implications.md b/qdrant-landing/content/course/multi-vector-search/module-3/memory-implications.md
deleted file mode 100644
index 4bcd68f76..000000000
--- a/qdrant-landing/content/course/multi-vector-search/module-3/memory-implications.md
+++ /dev/null
@@ -1,29 +0,0 @@
----
-title: "Memory Usage Implications"
-description: Understand the memory challenges of multi-vector search and overview of optimization techniques.
-weight: 1
----
-
-{{< date >}} Module 3 {{< /date >}}
-
-# Memory Usage Implications
-
-Multi-vector search can consume 10-100x more memory than single-vector search. Before deploying to production, you need to understand why this happens and what you can do about it.
-
-This lesson sets the stage for the optimization techniques we'll explore in the rest of Module 3.
-
----
-
-<div class="video">
-<iframe
-  src="https://www.youtube.com/embed/dQw4w9WgXcQ"
-  frameborder="0"
-  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
-  referrerpolicy="strict-origin-when-cross-origin"
-  allowfullscreen>
-</iframe>
-</div>
-
----
-
-Let's start optimizing. First up: vector quantization techniques to reduce memory usage.
diff --git a/qdrant-landing/content/course/multi-vector-search/module-3/multi-stage-retrieval.md b/qdrant-landing/content/course/multi-vector-search/module-3/multi-stage-retrieval.md
index e40959b0f..3c8d73bfb 100644
--- a/qdrant-landing/content/course/multi-vector-search/module-3/multi-stage-retrieval.md
+++ b/qdrant-landing/content/course/multi-vector-search/module-3/multi-stage-retrieval.md
@@ -1,7 +1,7 @@
 ---
 title: "Multi-Stage Retrieval with Universal Query API"
 description: Combine multiple optimization techniques in multi-stage retrieval pipelines using Qdrant's Universal Query API.
-weight: 5
+weight: 1
 ---
 
 {{< date >}} Module 3 {{< /date >}}