diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index f9d20fee5..8684771e2 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -692,6 +692,7 @@ struct server_context {
 
             auto params_dft = params_base;
 
+            params_dft.devices      = params_base.speculative.devices;
             params_dft.model        = params_base.speculative.model;
             params_dft.n_ctx        = params_base.speculative.n_ctx;
             params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers;
diff --git a/examples/speculative-simple/speculative-simple.cpp b/examples/speculative-simple/speculative-simple.cpp
index 1bc7f428c..7bf9056bf 100644
--- a/examples/speculative-simple/speculative-simple.cpp
+++ b/examples/speculative-simple/speculative-simple.cpp
@@ -46,6 +46,7 @@ int main(int argc, char ** argv) {
     ctx_tgt   = llama_init_tgt.context;
 
     // load the draft model
+    params.devices      = params.speculative.devices;
     params.model        = params.speculative.model;
     params.n_ctx        = params.speculative.n_ctx;
     params.n_batch      = params.speculative.n_ctx > 0 ? params.speculative.n_ctx : params.n_batch;