diff --git a/src/plugins/intel_npu/src/plugin/npuw/compiled_model.cpp b/src/plugins/intel_npu/src/plugin/npuw/compiled_model.cpp
index 0a16483016edd8..44ec0610bddafb 100644
--- a/src/plugins/intel_npu/src/plugin/npuw/compiled_model.cpp
+++ b/src/plugins/intel_npu/src/plugin/npuw/compiled_model.cpp
@@ -788,7 +788,7 @@ std::shared_ptr<ov::npuw::CompiledModel> ov::npuw::CompiledModel::deserialize(
     compiled->m_compiled_submodels.reserve(subm_size);
     for (std::size_t i = 0; i < subm_size; ++i) {
         auto desc = CompiledModelDesc::deserialize(stream, i, plugin, non_npuw_props);
-        desc.device_it = compiled->m_dev_list.cbegin();  // FIXME: only NPU device is supported for now
+        desc.device_it = compiled->m_dev_list.cbegin();
         compiled->m_compiled_submodels.push_back(desc);
     }
 
diff --git a/src/plugins/intel_npu/src/plugin/npuw/llm_compiled_model.cpp b/src/plugins/intel_npu/src/plugin/npuw/llm_compiled_model.cpp
index baeee604546c42..18bce01c2ba984 100644
--- a/src/plugins/intel_npu/src/plugin/npuw/llm_compiled_model.cpp
+++ b/src/plugins/intel_npu/src/plugin/npuw/llm_compiled_model.cpp
@@ -429,11 +429,6 @@ ov::npuw::LLMCompiledModel::LLMCompiledModel(const std::shared_ptr<ov::Model>& m
 
     m_cfg.update(any_copy(npuw_llm_props));
 
-    if (!model) {
-        LOG_DEBUG("LLMCompiledModel is being deserialized, skipping the full constructor flow...");
-        return;
-    }
-
     if (m_name.find(npuw_name_identifier) != m_name.npos) {
         LOG_DEBUG("LLMCompiledModel is being deserialized, skipping the full constructor flow...");
         return;