diff --git a/src/core/gpu_commands.cpp b/src/core/gpu_commands.cpp
index a57f6c421..cdcd5a4d5 100644
--- a/src/core/gpu_commands.cpp
+++ b/src/core/gpu_commands.cpp
@@ -5,7 +5,6 @@
 #include "gpu.h"
 #include "gpu_backend.h"
 #include "gpu_dump.h"
-#include "gpu_hw_texture_cache.h"
 #include "gpu_thread_commands.h"
 #include "interrupt_controller.h"
 #include "system.h"
@@ -1048,12 +1047,6 @@ void GPU::FinishVRAMWrite()
                      m_vram_transfer.height, sizeof(u16) * m_vram_transfer.width, m_blit_buffer.data(), true);
     }
 
-    if (GPUTextureCache::ShouldDumpVRAMWrite(m_vram_transfer.width, m_vram_transfer.height))
-    {
-      GPUTextureCache::DumpVRAMWrite(m_vram_transfer.width, m_vram_transfer.height,
-                                     reinterpret_cast<const u16*>(m_blit_buffer.data()));
-    }
-
     UpdateVRAM(m_vram_transfer.x, m_vram_transfer.y, m_vram_transfer.width, m_vram_transfer.height,
                m_blit_buffer.data(), m_GPUSTAT.set_mask_while_drawing, m_GPUSTAT.check_mask_before_draw);
   }
diff --git a/src/core/gpu_hw.cpp b/src/core/gpu_hw.cpp
index 64c4a8d53..d4b2054ba 100644
--- a/src/core/gpu_hw.cpp
+++ b/src/core/gpu_hw.cpp
@@ -3243,6 +3243,10 @@ void GPU_HW::UpdateVRAM(u32 x, u32 y, u32 width, u32 height, const void* data, b
   }
   else
   {
+    // no point dumping things we can't replace, so put it after the mask check
+    if (GPUTextureCache::ShouldDumpVRAMWrite(width, height))
+      GPUTextureCache::DumpVRAMWrite(width, height, data);
+
     GPUTexture* rtex = GPUTextureCache::GetVRAMReplacement(width, height, data);
     if (rtex && BlitVRAMReplacementTexture(rtex, x * m_resolution_scale, y * m_resolution_scale,
                                            width * m_resolution_scale, height * m_resolution_scale))