diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp
index 03b7951c3cc1..25693527ba82 100644
--- a/src/llama-arch.cpp
+++ b/src/llama-arch.cpp
@@ -1158,7 +1158,6 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
         case LLM_ARCH_BAILINGMOE3:
         case LLM_ARCH_KIMI_K3:
         case LLM_ARCH_QWEN3TTS:
-        case LLM_ARCH_QWEN4EXP:   // TODO: fix test-llama-archs
             return false;
         default:
             return true;
diff --git a/src/models/qwen4exp.cpp b/src/models/qwen4exp.cpp
index f33989de023d..b4184bba83cb 100644
--- a/src/models/qwen4exp.cpp
+++ b/src/models/qwen4exp.cpp
@@ -390,6 +390,8 @@ llama_model_qwen4exp::graph::graph(const llama_model & model, const llm_graph_pa
             ggml_reshape_3d(ctx0, inpL, n_embd, 1, n_tokens),
             n_embd, hc, n_tokens, 1);
     cb(res_hc, "hc_init", -1);
+    // make sure hc_init is in the same graph split as the first layer (-sm tensor)
+    ggml_build_forward_expand(gf, res_hc);
 
     for (int il = 0; il < n_layer; ++il) {
         res->t_layer_inp[il] = res_hc;