diff --git a/tensorflow/lite/experimental/ruy/kernel.h b/tensorflow/lite/experimental/ruy/kernel.h
index fae8515790e..80402b046a2 100644
--- a/tensorflow/lite/experimental/ruy/kernel.h
+++ b/tensorflow/lite/experimental/ruy/kernel.h
@@ -453,8 +453,8 @@ void KernelFloatNeonDotprodInOrder(const KernelParamsFloat<8, 8>& params);
 template <>
 struct Kernel<Path::kNeon, float, float, float, BasicSpec<float, float>> {
   Tuning tuning = Tuning::kAuto;
-  using LhsLayout = FixedKernelLayout<Order::kRowMajor, 1, 8>;
-  using RhsLayout = FixedKernelLayout<Order::kRowMajor, 1, 8>;
+  using LhsLayout = FixedKernelLayout<Order::kRowMajor, 4, 8>;
+  using RhsLayout = FixedKernelLayout<Order::kRowMajor, 4, 8>;
   explicit Kernel(Tuning tuning_) : tuning(tuning_) {}
   void Run(const PackedMatrix<float>& lhs, const PackedMatrix<float>& rhs,
            const BasicSpec<float, float>& spec, int start_row, int start_col,
diff --git a/tensorflow/lite/experimental/ruy/pack.h b/tensorflow/lite/experimental/ruy/pack.h
index 520099cabfc..556821087d7 100644
--- a/tensorflow/lite/experimental/ruy/pack.h
+++ b/tensorflow/lite/experimental/ruy/pack.h
@@ -262,7 +262,7 @@ void PackFloatNeonInOrder(const float* src_ptr0, const float* src_ptr1,
                           float* packed_ptr, int start_col, int end_col);
 
 template <>
-struct PackImpl<Path::kNeon, FixedKernelLayout<Order::kRowMajor, 1, 8>, float,
+struct PackImpl<Path::kNeon, FixedKernelLayout<Order::kRowMajor, 4, 8>, float,
                 float, float> {
   static void Run(Tuning tuning, const Matrix<float>& src_matrix,
                   PackedMatrix<float>* packed_matrix, int start_col,