diff --git a/src/models/qwen4exp.cpp b/src/models/qwen4exp.cpp
index 2074b2f14f..0a58d6d9aa 100644
--- a/src/models/qwen4exp.cpp
+++ b/src/models/qwen4exp.cpp
@@ -686,7 +686,7 @@ ggml_tensor * llama_model_qwen4exp::graph::build_attn_qsa(
     ggml_tensor * k = mctx_cur->get_k(ctx0, il);
     ggml_tensor * v = mctx_cur->get_v(ctx0, il);
 
-    ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, 0, kq_scale, il);
+    ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, top_k->ne[0], kq_scale, il);
     cb(cur, "kqv_out", il);
 
     // the rotation is its own inverse, so undo it on the value side of the output