diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 85db938a7a..3712e3169b 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -7515,6 +7515,65 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
             if (!layer.ssm_beta_s && layer.ssm_beta) {
                 layer.ssm_beta_s = create_tensor(tn(LLM_TENSOR_SSM_BETA, "scale", i), {1}, TENSOR_NOT_REQUIRED);
             }
+
+            // input scales
+            if (!layer.wq_in_s && layer.wq) {
+                layer.wq_in_s = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.wk_in_s && layer.wk) {
+                layer.wk_in_s = create_tensor(tn(LLM_TENSOR_ATTN_K,   "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.wv_in_s && layer.wv) {
+                layer.wv_in_s = create_tensor(tn(LLM_TENSOR_ATTN_V,   "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.wo_in_s && layer.wo) {
+                layer.wo_in_s = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.wqkv_in_s && layer.wqkv) {
+                layer.wqkv_in_s = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.wqkv_gate_in_s && layer.wqkv_gate) {
+                layer.wqkv_gate_in_s = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_gate_in_s && layer.ffn_gate) {
+                layer.ffn_gate_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_down_in_s && layer.ffn_down) {
+                layer.ffn_down_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_up_in_s && layer.ffn_up) {
+                layer.ffn_up_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_gate_exps_in_s && layer.ffn_gate_exps) {
+                layer.ffn_gate_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_down_exps_in_s && layer.ffn_down_exps) {
+                layer.ffn_down_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_up_exps_in_s && layer.ffn_up_exps) {
+                layer.ffn_up_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_gate_shexp_in_s && layer.ffn_gate_shexp) {
+                layer.ffn_gate_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_down_shexp_in_s && layer.ffn_down_shexp) {
+                layer.ffn_down_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ffn_up_shexp_in_s && layer.ffn_up_shexp) {
+                layer.ffn_up_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ssm_in_in_s && layer.ssm_in) {
+                layer.ssm_in_in_s = create_tensor(tn(LLM_TENSOR_SSM_IN, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ssm_out_in_s && layer.ssm_out) {
+                layer.ssm_out_in_s = create_tensor(tn(LLM_TENSOR_SSM_OUT, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ssm_alpha_in_s && layer.ssm_alpha) {
+                layer.ssm_alpha_in_s = create_tensor(tn(LLM_TENSOR_SSM_ALPHA, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
+            if (!layer.ssm_beta_in_s && layer.ssm_beta) {
+                layer.ssm_beta_in_s = create_tensor(tn(LLM_TENSOR_SSM_BETA, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
+            }
         }
     }
 
diff --git a/src/llama-model.h b/src/llama-model.h
index aefcfe700f..96ab31cbb0 100644
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -414,6 +414,27 @@ struct llama_layer {
     struct ggml_tensor * ssm_alpha_s = nullptr;
     struct ggml_tensor * ssm_beta_s  = nullptr;
 
+    // input scales
+    struct ggml_tensor * wq_in_s            = nullptr;
+    struct ggml_tensor * wk_in_s            = nullptr;
+    struct ggml_tensor * wv_in_s            = nullptr;
+    struct ggml_tensor * wo_in_s            = nullptr;
+    struct ggml_tensor * wqkv_in_s          = nullptr;
+    struct ggml_tensor * wqkv_gate_in_s     = nullptr;
+    struct ggml_tensor * ffn_gate_in_s      = nullptr;
+    struct ggml_tensor * ffn_up_in_s        = nullptr;
+    struct ggml_tensor * ffn_down_in_s      = nullptr;
+    struct ggml_tensor * ffn_gate_exps_in_s = nullptr;
+    struct ggml_tensor * ffn_down_exps_in_s = nullptr;
+    struct ggml_tensor * ffn_up_exps_in_s   = nullptr;
+    struct ggml_tensor * ffn_gate_shexp_in_s= nullptr;
+    struct ggml_tensor * ffn_up_shexp_in_s  = nullptr;
+    struct ggml_tensor * ffn_down_shexp_in_s= nullptr;
+    struct ggml_tensor * ssm_in_in_s        = nullptr;
+    struct ggml_tensor * ssm_out_in_s       = nullptr;
+    struct ggml_tensor * ssm_alpha_in_s     = nullptr;
+    struct ggml_tensor * ssm_beta_in_s      = nullptr;
+
     // altup & laurel
     struct ggml_tensor * per_layer_inp_gate   = nullptr;
     struct ggml_tensor * per_layer_proj       = nullptr;