diff --git a/example/ck_tile/38_block_scale_gemm/README.md b/example/ck_tile/38_block_scale_gemm/README.md
index 496697ca32..c69703e50c 100644
--- a/example/ck_tile/38_block_scale_gemm/README.md
+++ b/example/ck_tile/38_block_scale_gemm/README.md
@@ -64,8 +64,10 @@ User need to select correct mapping of config for each quant mode:
 |  | quant_mode as runtime argument | Config in cpp file |
 |:--------|:-----:|-------|
 | For selecting AQuant  | aquant  | GemmConfigQuant    |
-| For selecting Aquant with Preshuffle   | aquant  | GemmConfigPreshuffleQuant    |
+| For selecting AQuant with Preshuffle    | aquant  | GemmConfigPreshuffleQuant    |
 | For selecting BQuant  | bquant  | GemmConfigQuant    |
-| For selecting PreShuffle Weight matrix with Bquant | bquant | GemmConfigPreshuffleB_Bquant_decode (or) GemmConfigPreshuffleB_Bquant_prefill
+| For selecting BQuant  with Preshuffle  | bquant  | GemmConfigPreshuffleQuant    |
+| For selecting PreShuffle B with BQuant | bquant | GemmConfigPreshuffleB_BQuant_Decode (or) GemmConfigPreshuffleB_BQuant_Prefill
+| For selecting PreShuffle B with preshuffle BQuant | bquant | GemmConfigPreshuffleB_PreshuffleBQuant_Decode (or) GemmConfigPreshuffleB_PreshuffleBQuant_Prefill
 | For selecting RowCol quant  | rowcolquant  | GemmConfigRowColQuant    |
 
diff --git a/example/ck_tile/38_block_scale_gemm/gemm_quant_basic.cpp b/example/ck_tile/38_block_scale_gemm/gemm_quant_basic.cpp
index 63f76c5459..46cb017335 100644
--- a/example/ck_tile/38_block_scale_gemm/gemm_quant_basic.cpp
+++ b/example/ck_tile/38_block_scale_gemm/gemm_quant_basic.cpp
@@ -460,5 +460,5 @@ int run_gemm_example(int argc, char* argv[])
 
 int main(int argc, char* argv[])
 {
-    return !run_gemm_example<GemmConfigPreshuffleB_Bquant_decode>(argc, argv);
+    return !run_gemm_example<GemmConfigPreshuffleB_PreshuffleBQuant_Prefill>(argc, argv);
 }
diff --git a/example/ck_tile/38_block_scale_gemm/gemm_utils.hpp b/example/ck_tile/38_block_scale_gemm/gemm_utils.hpp
index 8322efd006..aed6d40df8 100644
--- a/example/ck_tile/38_block_scale_gemm/gemm_utils.hpp
+++ b/example/ck_tile/38_block_scale_gemm/gemm_utils.hpp
@@ -148,7 +148,30 @@ struct GemmConfigPreshuffleQuant : public GemmConfigBase
 };
 
 template <typename PrecType>
-struct GemmConfigPreshuffleB_Bquant_decode : public GemmConfigBase
+struct GemmConfigPreshuffleB_BQuant_Decode : public GemmConfigBase
+{
+    static constexpr ck_tile::index_t M_Tile = 16;
+    static constexpr ck_tile::index_t N_Tile = 64;
+    static constexpr ck_tile::index_t K_Tile = 256 / sizeof(PrecType);
+
+    static constexpr ck_tile::index_t M_Warp = 1;
+    static constexpr ck_tile::index_t N_Warp = 4;
+    static constexpr ck_tile::index_t K_Warp = 1;
+
+    static constexpr ck_tile::index_t M_Warp_Tile = 16;
+    static constexpr ck_tile::index_t N_Warp_Tile = 16;
+    static constexpr ck_tile::index_t K_Warp_Tile =
+        get_k_from_preshuffled_warp_tile<PrecType, M_Warp_Tile>();
+
+    static constexpr bool PreshuffleB      = true;
+    static constexpr bool DoubleSmemBuffer = true;
+
+    static constexpr int N_Repeat          = N_Tile / N_Warp_Tile / N_Warp;
+    static constexpr bool TiledMMAPermuteN = N_Repeat % 2 == 0;
+};
+
+template <typename PrecType>
+struct GemmConfigPreshuffleB_PreshuffleBQuant_Decode : public GemmConfigBase
 {
     static constexpr ck_tile::index_t M_Tile = 16;
     static constexpr ck_tile::index_t N_Tile = 64;
@@ -166,13 +189,10 @@ struct GemmConfigPreshuffleB_Bquant_decode : public GemmConfigBase
     static constexpr bool PreshuffleB      = true;
     static constexpr bool DoubleSmemBuffer = true;
     static constexpr bool PreshuffleQuant  = true;
-
-    static constexpr int N_Repeat          = N_Tile / N_Warp_Tile / N_Warp;
-    static constexpr bool TiledMMAPermuteN = N_Repeat % 2 == 0;
 };
 
 template <typename PrecType>
-struct GemmConfigPreshuffleB_Bquant_prefill : public GemmConfigBase
+struct GemmConfigPreshuffleB_BQuant_Prefill : public GemmConfigBase
 {
     static constexpr ck_tile::index_t M_Tile = 128;
     static constexpr ck_tile::index_t N_Tile = 128;
@@ -194,6 +214,27 @@ struct GemmConfigPreshuffleB_Bquant_prefill : public GemmConfigBase
     static constexpr bool TiledMMAPermuteN = N_Repeat % 2 == 0;
 };
 
+template <typename PrecType>
+struct GemmConfigPreshuffleB_PreshuffleBQuant_Prefill : public GemmConfigBase
+{
+    static constexpr ck_tile::index_t M_Tile = 128;
+    static constexpr ck_tile::index_t N_Tile = 128;
+    static constexpr ck_tile::index_t K_Tile = 128 / sizeof(PrecType);
+
+    static constexpr ck_tile::index_t M_Warp = 1;
+    static constexpr ck_tile::index_t N_Warp = 4;
+    static constexpr ck_tile::index_t K_Warp = 1;
+
+    static constexpr ck_tile::index_t M_Warp_Tile = 16;
+    static constexpr ck_tile::index_t N_Warp_Tile = 16;
+    static constexpr ck_tile::index_t K_Warp_Tile =
+        get_k_from_preshuffled_warp_tile<PrecType, M_Warp_Tile>();
+
+    static constexpr bool PreshuffleB      = true;
+    static constexpr bool DoubleSmemBuffer = true;
+    static constexpr bool PreshuffleQuant  = true;
+};
+
 template <typename ADataType_,
           typename BDataType_ = ADataType_,
           typename CDataType_ = ADataType_,