diff --git a/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml b/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml
index 19cacdef178..3dbdb802796 100644
--- a/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml
+++ b/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml
@@ -32,3 +32,12 @@ conv2d_dw_output_tile:
       OPERATOR: clamp(X, A, B)
       BATCH_SIZE_X: 1
       BATCH_SIZE_Y: 1
+    - NAME: conv2d_dw_output_tile_5x5_b1x1
+      TILE_SIZE: 5
+      BATCH_SIZE_X: 1
+      BATCH_SIZE_Y: 1
+    - NAME: conv2d_dw_output_tile_5x5_b1x1_clamp
+      OPERATOR: clamp(X, A, B)
+      TILE_SIZE: 5
+      BATCH_SIZE_X: 1
+      BATCH_SIZE_Y: 1
diff --git a/backends/vulkan/runtime/graph/ops/impl/Conv2dDW.cpp b/backends/vulkan/runtime/graph/ops/impl/Conv2dDW.cpp
index a9d8483b2e2..74649051635 100644
--- a/backends/vulkan/runtime/graph/ops/impl/Conv2dDW.cpp
+++ b/backends/vulkan/runtime/graph/ops/impl/Conv2dDW.cpp
@@ -81,13 +81,13 @@ std::string pick_conv2d_dw_shader(
     kernel_name += "_sned";
   }
 
-  if (is_3x3) {
-    kernel_name += "_output_tile_3x3";
+  if (is_3x3 || is_5x5) {
+    kernel_name += is_3x3 ? "_output_tile_3x3" : "_output_tile_5x5";
+    // Mali spills with the default 4x2 output tile: each invocation holds 8
+    // accumulators and loads an overlapping input window for each of them.
     if (stride_equals_dilation && graph.device_is_mali()) {
       kernel_name += "_b1x1";
     }
-  } else if (is_5x5) {
-    kernel_name += "_output_tile_5x5";
   }
 
   if (clamp_out) {