diff --git a/common/common.h b/common/common.h
index 16a94408cc8c..eb50a6cbc520 100644
--- a/common/common.h
+++ b/common/common.h
@@ -386,7 +386,7 @@ struct common_params_speculative {
 
     uint32_t need_n_rs_seq() const {
         bool needs_rs_seq = std::any_of(types.begin(), types.end(), [&](auto t) {
-            return t == COMMON_SPECULATIVE_TYPE_DRAFT_MTP || t == COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3 || t == COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH || t == COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK;
+            return t == COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE || t == COMMON_SPECULATIVE_TYPE_DRAFT_MTP || t == COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3 || t == COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH || t == COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK;
         });
 
         return needs_rs_seq ? draft.n_max : 0u;
diff --git a/common/speculative.cpp b/common/speculative.cpp
index 1ff0ddeb7e0c..df5c965406fd 100644
--- a/common/speculative.cpp
+++ b/common/speculative.cpp
@@ -2416,9 +2416,10 @@ common_speculative_init_result::common_speculative_init_result(
     // the draft context holds as many tokens per sequence as the target context
     cparams.n_ctx = llama_n_ctx(ctx_tgt);
 
-    // note: for small models maybe we can set this to the maximum possible draft from all speculative types
-    //       the extra memory for small models is likely negligible?
-    cparams.n_rs_seq  = 0;
+    // the draft context must reserve the same per-sequence recurrent-state slots as the target.
+    // leaving this at 0 makes common_context_can_seq_rm() classify the context as FULL, so
+    // llama_memory_seq_rm() silently fails on it and stale positions are retained.
+    cparams.n_rs_seq  = params.speculative.need_n_rs_seq();
     cparams.ctx_other = ctx_tgt;
 
     std::string model_path;