diff --git a/src/cpu/operators/CpuDepthwiseConv2d.cpp b/src/cpu/operators/CpuDepthwiseConv2d.cpp
index f69ecdc..ea451a4 100644
--- a/src/cpu/operators/CpuDepthwiseConv2d.cpp
+++ b/src/cpu/operators/CpuDepthwiseConv2d.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2022 Arm Limited.
+ * Copyright (c) 2021-2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -461,6 +461,8 @@
 
 Status CpuDepthwiseConv2d::validate(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *dst, const ConvolutionInfo &info)
 {
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!weights->are_values_constant(), "Dynamic weights are not supported");
+
     DepthwiseConvolutionFunction depth_conv_func = get_depthwiseconvolution_function(src, weights, biases, dst, info);
     switch(depth_conv_func)
     {
diff --git a/src/dynamic_fusion/sketch/gpu/operators/GpuConv2d.cpp b/src/dynamic_fusion/sketch/gpu/operators/GpuConv2d.cpp
index d29d848..cb270ed 100644
--- a/src/dynamic_fusion/sketch/gpu/operators/GpuConv2d.cpp
+++ b/src/dynamic_fusion/sketch/gpu/operators/GpuConv2d.cpp
@@ -145,6 +145,7 @@
                               const Conv2dAttributes &attributes)
 {
     ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(src, wei);
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!wei->are_values_constant(), "Dynamic weights are not supported");
 
     // Check if tensors have valid id. I.e. they are created from a sketch
     ARM_COMPUTE_RETURN_ERROR_ON(!src->has_valid_id() || !wei->has_valid_id());
diff --git a/src/dynamic_fusion/sketch/gpu/operators/GpuDepthwiseConv2d.cpp b/src/dynamic_fusion/sketch/gpu/operators/GpuDepthwiseConv2d.cpp
index 0f9e726..c72098e 100644
--- a/src/dynamic_fusion/sketch/gpu/operators/GpuDepthwiseConv2d.cpp
+++ b/src/dynamic_fusion/sketch/gpu/operators/GpuDepthwiseConv2d.cpp
@@ -154,6 +154,8 @@
                                        const DepthwiseConv2dAttributes &attributes)
 {
     ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(src, wei);
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!wei->are_values_constant(), "Dynamic weights are not supported");
+
     ARM_COMPUTE_RETURN_ERROR_ON(!src->has_valid_id() || !wei->has_valid_id());
 
     if(bia != nullptr)
diff --git a/src/runtime/CL/functions/CLConvolutionLayer.cpp b/src/runtime/CL/functions/CLConvolutionLayer.cpp
index 384249f..476bf27 100644
--- a/src/runtime/CL/functions/CLConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLConvolutionLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Arm Limited.
+ * Copyright (c) 2017-2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -130,6 +130,7 @@
                                     const WeightsInfo &weights_info, const Size2D &dilation, const ActivationLayerInfo &act_info, bool enable_fast_math, unsigned int num_groups, const experimental::PostOpList<ITensorInfo *> &post_ops)
 {
     ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input, weights, output);
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!weights->are_values_constant(), "Dynamic weights are not supported");
     ARM_COMPUTE_RETURN_ERROR_ON_MSG((num_groups != 1) && (input->data_layout() != DataLayout::NCHW), "Grouping (num_groups != 1) with NHWC data layout is not supported");
 
     const GPUTarget  gpu_target  = CLScheduler::get().target();
diff --git a/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp b/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
index 3909c15..dcb982f 100644
--- a/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Arm Limited.
+ * Copyright (c) 2017-2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -162,6 +162,9 @@
                                              const PadStrideInfo &conv_info,
                                              unsigned int depth_multiplier, ActivationLayerInfo act_info, const Size2D &dilation)
 {
+    ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input, weights);
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!weights->are_values_constant(), "Dynamic weights are not supported");
+
     const bool in_place = input == output || output == nullptr;
     if(in_place)
     {
diff --git a/src/runtime/NEON/functions/NEConvolutionLayer.cpp b/src/runtime/NEON/functions/NEConvolutionLayer.cpp
index 317f463..89e0e49 100644
--- a/src/runtime/NEON/functions/NEConvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEConvolutionLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2021 Arm Limited.
+ * Copyright (c) 2017-2021, 2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -108,6 +108,9 @@
                                     const WeightsInfo &weights_info, const Size2D &dilation, const ActivationLayerInfo &act_info, bool enable_fast_math, unsigned int num_groups)
 {
     const Conv2dInfo info(conv_info, dilation, act_info, enable_fast_math, num_groups);
+
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(!weights->are_values_constant(), "Dynamic weights are not supported");
+
     switch(cpu::CpuConv2d::get_convolution_method(input, weights, output, conv_info, weights_info, dilation, act_info, enable_fast_math))
     {
         case ConvolutionMethod::WINOGRAD: