diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu
index 7fee71d84..67d9828cb 100644
--- a/ggml/src/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda.cu
@@ -1647,7 +1647,7 @@ static void ggml_cuda_op_mul_mat(
     }
 
     const int64_t src1_col_stride = split && used_devices > 1 ? MUL_MAT_SRC1_COL_STRIDE : ne11;
-    if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1) {
+    if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1 && ne02 == ne12 && ne02 == dst->ne[2]) {
         //printf("invoking fast path for %s x %s\n", src0->name, src1->name);
         int id = ctx.device;
         char  *  src0_dd_i =  dev[id].src0_dd;
diff --git a/ggml/src/ggml-cuda/mmq.cu b/ggml/src/ggml-cuda/mmq.cu
index a0e7da129..1e3accf07 100644
--- a/ggml/src/ggml-cuda/mmq.cu
+++ b/ggml/src/ggml-cuda/mmq.cu
@@ -14,7 +14,7 @@ void ggml_cuda_op_mul_mat_q(
     const int64_t src1_padded_row_size, cudaStream_t stream) {
 
     const int64_t ne00 = src0->ne[0];
-    const int64_t nb01 = src0->nb[1];
+    const int64_t nb01 = ggml_row_size(src0->type, ne00);
 
     const int64_t ne10 = src1->ne[0];
     const int64_t ne11 = src1->ne[1];