diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 08fb392603..04b8f6d118 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -4549,7 +4549,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, ssm_num_heads}, 0);
                         layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, ssm_num_heads}, 0);
                         // ssm_norm
-                        layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {ssm_intermediate_size / ssm_n_groups, ssm_n_groups}, 0);
+                        layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {ssm_intermediate_size / ssm_n_groups, ssm_n_groups}, llama_model_loader::TENSOR_NOT_REQUIRED);
                         // out_proj
                         layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), {ssm_intermediate_size, hidden_size}, 0);