diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 5e1b512318..bbfc430b4d 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -8119,7 +8119,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
                         // For MTP: need room for active cell + checkpoint cells.
                         // With size=4: active(1) + checkpoint(1) + room(2) ensures
                         // can_checkpoint (used < size*0.9 = 3.6) can fire even with 3 cells in use.
-                        const uint32_t rs_per_seq = 1 + (n_mtp > 0 ? 3 : 0);
+                        const uint32_t rs_per_seq = 1 + (n_mtp > 0 ? 7 : 0);
                         const uint32_t rs_size = std::max((uint32_t) 1, cparams.n_seq_max * rs_per_seq);
 
                         res = new llama_memory_hybrid_iswa(