diff --git a/TracyOpenGL.hpp b/TracyOpenGL.hpp
index 58b17ba0..7690cd48 100644
--- a/TracyOpenGL.hpp
+++ b/TracyOpenGL.hpp
@@ -164,7 +164,8 @@ class GpuCtxScope
 public:
     tracy_force_inline GpuCtxScope( const SourceLocation* srcloc )
     {
-        glQueryCounter( s_gpuCtx.ptr->NextQueryId(), GL_TIMESTAMP );
+        const auto queryId = s_gpuCtx.ptr->NextQueryId();
+        glQueryCounter( queryId, GL_TIMESTAMP );
 
         Magic magic;
         auto& token = s_token.ptr;
@@ -174,13 +175,15 @@ public:
         MemWrite( &item->gpuZoneBegin.cpuTime, Profiler::GetTime() );
         MemWrite( &item->gpuZoneBegin.srcloc, (uint64_t)srcloc );
         memset( &item->gpuZoneBegin.thread, 0, sizeof( item->gpuZoneBegin.thread ) );
+        MemWrite( &item->gpuZoneBegin.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneBegin.context, s_gpuCtx.ptr->GetId() );
         tail.store( magic + 1, std::memory_order_release );
     }
 
     tracy_force_inline GpuCtxScope( const SourceLocation* srcloc, int depth )
     {
-        glQueryCounter( s_gpuCtx.ptr->NextQueryId(), GL_TIMESTAMP );
+        const auto queryId = s_gpuCtx.ptr->NextQueryId();
+        glQueryCounter( queryId, GL_TIMESTAMP );
 
         const auto thread = GetThreadHandle();
 
@@ -192,6 +195,7 @@ public:
         MemWrite( &item->gpuZoneBegin.cpuTime, Profiler::GetTime() );
         MemWrite( &item->gpuZoneBegin.srcloc, (uint64_t)srcloc );
         MemWrite( &item->gpuZoneBegin.thread, thread );
+        MemWrite( &item->gpuZoneBegin.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneBegin.context, s_gpuCtx.ptr->GetId() );
         tail.store( magic + 1, std::memory_order_release );
 
@@ -200,7 +204,8 @@ public:
 
     tracy_force_inline ~GpuCtxScope()
     {
-        glQueryCounter( s_gpuCtx.ptr->NextQueryId(), GL_TIMESTAMP );
+        const auto queryId = s_gpuCtx.ptr->NextQueryId();
+        glQueryCounter( queryId, GL_TIMESTAMP );
 
         Magic magic;
         auto& token = s_token.ptr;
@@ -208,6 +213,7 @@ public:
         auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
         MemWrite( &item->hdr.type, QueueType::GpuZoneEnd );
         MemWrite( &item->gpuZoneEnd.cpuTime, Profiler::GetTime() );
+        MemWrite( &item->gpuZoneEnd.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneEnd.context, s_gpuCtx.ptr->GetId() );
         tail.store( magic + 1, std::memory_order_release );
     }
diff --git a/TracyVulkan.hpp b/TracyVulkan.hpp
index 8ea81237..d0c45abe 100644
--- a/TracyVulkan.hpp
+++ b/TracyVulkan.hpp
@@ -195,7 +195,8 @@ public:
         : m_cmdbuf( cmdbuf )
     {
         auto ctx = s_vkCtx.ptr;
-        vkCmdWriteTimestamp( cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, ctx->NextQueryId() );
+        const auto queryId = ctx->NextQueryId();
+        vkCmdWriteTimestamp( cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, queryId );
 
         Magic magic;
         auto& token = s_token.ptr;
@@ -205,6 +206,7 @@ public:
         MemWrite( &item->gpuZoneBegin.cpuTime, Profiler::GetTime() );
         MemWrite( &item->gpuZoneBegin.srcloc, (uint64_t)srcloc );
         MemWrite( &item->gpuZoneBegin.thread, GetThreadHandle() );
+        MemWrite( &item->gpuZoneBegin.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneBegin.context, ctx->GetId() );
         tail.store( magic + 1, std::memory_order_release );
     }
@@ -215,7 +217,8 @@ public:
         const auto thread = GetThreadHandle();
 
         auto ctx = s_vkCtx.ptr;
-        vkCmdWriteTimestamp( cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, ctx->NextQueryId() );
+        const auto queryId = ctx->NextQueryId();
+        vkCmdWriteTimestamp( cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, queryId );
 
         Magic magic;
         auto& token = s_token.ptr;
@@ -225,6 +228,7 @@ public:
         MemWrite( &item->gpuZoneBegin.cpuTime, Profiler::GetTime() );
         MemWrite( &item->gpuZoneBegin.srcloc, (uint64_t)srcloc );
         MemWrite( &item->gpuZoneBegin.thread, thread );
+        MemWrite( &item->gpuZoneBegin.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneBegin.context, ctx->GetId() );
         tail.store( magic + 1, std::memory_order_release );
 
@@ -234,7 +238,8 @@ public:
     tracy_force_inline ~VkCtxScope()
     {
         auto ctx = s_vkCtx.ptr;
-        vkCmdWriteTimestamp( m_cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, ctx->NextQueryId() );
+        const auto queryId = ctx->NextQueryId();
+        vkCmdWriteTimestamp( m_cmdbuf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, ctx->m_query, queryId );
 
         Magic magic;
         auto& token = s_token.ptr;
@@ -242,6 +247,7 @@ public:
         auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
         MemWrite( &item->hdr.type, QueueType::GpuZoneEnd );
         MemWrite( &item->gpuZoneEnd.cpuTime, Profiler::GetTime() );
+        MemWrite( &item->gpuZoneEnd.queryId, uint16_t( queryId ) );
         MemWrite( &item->gpuZoneEnd.context, ctx->GetId() );
         tail.store( magic + 1, std::memory_order_release );
     }
diff --git a/common/TracyQueue.hpp b/common/TracyQueue.hpp
index 52b7f2b9..504e0870 100644
--- a/common/TracyQueue.hpp
+++ b/common/TracyQueue.hpp
@@ -177,12 +177,14 @@ struct QueueGpuZoneBegin
     int64_t cpuTime;
     uint64_t srcloc;
     uint64_t thread;
+    uint16_t queryId;
     uint8_t context;
 };
 
 struct QueueGpuZoneEnd
 {
     int64_t cpuTime;
+    uint16_t queryId;
     uint8_t context;
 };