diff --git a/llama.cpp b/llama.cpp
index 000346f45..d3f472d9c 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -4728,10 +4728,10 @@ static bool llm_load_tensors(
 
                     layer.attn_out_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd});
 
-                    layer.ffn_gate_inp  = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert});
-                    layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS,"weight", i), {n_embd, n_ff,   n_expert});
-                    layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS,"weight", i), {n_ff,   n_embd, n_expert});
-                    layer.ffn_up_exps   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS,  "weight", i), {n_embd, n_ff,   n_expert});
+                    layer.ffn_gate_inp  = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), {n_embd, n_expert});
+                    layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff,   n_expert});
+                    layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff,   n_embd, n_expert});
+                    layer.ffn_up_exps   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {n_embd, n_ff,   n_expert});
                 }
             } break;
             case LLM_ARCH_BAICHUAN: