diff --git a/example/67_gemm_microscaling/gemm_mx_fp8.cpp b/example/67_gemm_microscaling/gemm_mx_fp8.cpp
index ccff1462e2..e6fe791178 100644
--- a/example/67_gemm_microscaling/gemm_mx_fp8.cpp
+++ b/example/67_gemm_microscaling/gemm_mx_fp8.cpp
@@ -53,20 +53,20 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMX_Xdl_CShuffle
     16,               // NPerXDL
     4,                // MXdlPerWave
     4,                // NXdlPerWave
-    S<8, 32, 1>,      // ABlockTransferThreadClusterLengths_AK0_M_AK1
+    S<16, 16, 1>,     // ABlockTransferThreadClusterLengths_AK0_M_AK1
     S<1, 0, 2>,       // ABlockTransferThreadClusterArrangeOrder
     S<1, 0, 2>,       // ABlockTransferSrcAccessOrder
     2,                // ABlockTransferSrcVectorDim
     16,               // ABlockTransferSrcScalarPerVector
     16,               // ABlockTransferDstScalarPerVector_AK1
-    false,            // ABlockLdsExtraM
-    S<8, 32, 1>,      // BBlockTransferThreadClusterLengths_BK0_N_BK1
+    true,             // ABlockLdsExtraM
+    S<16, 16, 1>,     // BBlockTransferThreadClusterLengths_BK0_N_BK1
     S<1, 0, 2>,       // BBlockTransferThreadClusterArrangeOrder
     S<1, 0, 2>,       // BBlockTransferSrcAccessOrder
     2,                // BBlockTransferSrcVectorDim
     16,               // BBlockTransferSrcScalarPerVector
     16,               // BBlockTransferDstScalarPerVector_BK1
-    false,            // BBlockLdsExtraN
+    true,             // BBlockLdsExtraN
     2,                // CShuffleMXdlPerWavePerShuffle
     2,                // CShuffleNXdlPerWavePerShuffle
     S<1, 32, 1, 8>,   // CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock