diff --git a/ggml/src/ggml-webgpu/ggml-webgpu.cpp b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
index b953118a7..1a43c7273 100644
--- a/ggml/src/ggml-webgpu/ggml-webgpu.cpp
+++ b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
@@ -3713,11 +3713,18 @@ static void ggml_backend_webgpu_buffer_get_tensor(ggml_backend_buffer_t buffer,
 
     size_t total_offset = ggml_webgpu_tensor_offset(tensor) + offset;
 
-    size_t final_size = size;
-    if (size % 4 != 0) {
+    size_t local_offset = total_offset % 4;
+    if (local_offset != 0) {
+        // If offset is not a multiple of 4, we need to round it down to the previous
+        // multiple of 4
+        total_offset -= local_offset;
+    }
+
+    size_t final_size = size + local_offset;
+    if (final_size % 4 != 0) {
         // If size is not a multiple of 4, we need to round it up to the next
         // multiple of 4
-        final_size = size + (4 - (size % 4));
+        final_size += 4 - (final_size % 4);
     }
 
     std::lock_guard<std::recursive_mutex> lock(buf_ctx->global_ctx->mutex);
@@ -3748,7 +3755,7 @@ static void ggml_backend_webgpu_buffer_get_tensor(ggml_backend_buffer_t buffer,
     const void * mapped_range = buf_ctx->global_ctx->get_tensor_staging_buf.GetConstMappedRange(0, final_size);
 
     // Copy the data from the mapped range to the output buffer
-    std::memcpy(data, mapped_range, size);
+    std::memcpy(data, (const void *) ((const char *) mapped_range + local_offset), size);
     buf_ctx->global_ctx->get_tensor_staging_buf.Unmap();
     WEBGPU_CPU_PROFILE_TOTAL_END(get_tensor, buf_ctx->global_ctx);
 }