diff --git a/common/arg.cpp b/common/arg.cpp
index 56827a65908be..b990046e1b95c 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -3423,5 +3423,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}));
 
+    add_opt(common_arg
+            ({ "--chat-smollm-3b-default" },
+            string_format("use default SmolLM-v3 3B model (note: can download weights from the internet)"),
+            [](common_params & params) {
+                params.model.hf_repo = "ggml-org/SmolLM3-3B-GGUF";
+                params.model.hf_file = "SmolLM3-Q8_0.gguf";
+                params.n_gpu_layers  = 40;
+                params.flash_attn    = true;
+                params.n_ubatch      = 1024;
+                params.n_batch       = 1024;
+                params.n_ctx         = 65536;
+                params.n_cache_reuse = 256;
+            }
+        ).set_examples({ LLAMA_EXAMPLE_SERVER }));
+
+
     return ctx_arg;
 }