diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp
index a85e97288..b52e3f620 100644
--- a/src/llama-graph.cpp
+++ b/src/llama-graph.cpp
@@ -803,6 +803,10 @@ ggml_tensor * llm_graph_context::build_ffn(
 
     if (down) {
         cur = build_lora_mm(down, cur);
+        if (arch == LLM_ARCH_GLM4) {
+            // GLM4 seems to have numerical issues with half-precision accumulators
+            ggml_mul_mat_set_prec(cur, GGML_PREC_F32);
+        }
     }
 
     if (down_b) {