diff --git a/src/llama-load-tensors.cpp b/src/llama-load-tensors.cpp
index 600ae256..717fa9c3 100644
--- a/src/llama-load-tensors.cpp
+++ b/src/llama-load-tensors.cpp
@@ -1298,7 +1298,12 @@ bool create_tensors_helper::create_gemma_tensors(const LLM_TN & tn, int version)
 
     // output
     model.output_norm = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
-    model.output      = create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED); // same as tok_embd, duplicated to allow offloading
+    model.output      = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab},
+            llama_model_loader::TENSOR_NOT_REQUIRED);
+    if (!model.output) {
+        model.output = create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab},
+                llama_model_loader::TENSOR_DUPLICATED);
+    }
 
     for (int i = 0; i < n_layer; ++i) {
         ggml_context * ctx_layer = ctx_for_layer(i);
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index dd627a4f..8ff29891 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -639,6 +639,7 @@ static const std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NA
         {
             { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
             { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
+            { LLM_TENSOR_OUTPUT,          "output" },
             { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
             { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
             { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },