diff --git a/examples/offline_inference/load_sharded_state.py b/examples/offline_inference/load_sharded_state.py
index 52c2363c89874..c5ae35985c17c 100644
--- a/examples/offline_inference/load_sharded_state.py
+++ b/examples/offline_inference/load_sharded_state.py
@@ -11,7 +11,7 @@ python save_sharded_state.py \
     --model /path/to/load \
     --quantization deepspeedfp \
     --tensor-parallel-size 8 \
-    --output /path/to/save/sharded/modele
+    --output /path/to/save/sharded/model
 
 python load_sharded_state.py \
     --model /path/to/saved/sharded/model \
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
index c225479810aa4..3709710ef42e7 100644
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
@@ -3035,7 +3035,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
             time_after_load = time.perf_counter()
         self.model_memory_usage = m.consumed_memory
         logger.info_once(
-            "Model loading took %.4f GiB and %.6f seconds",
+            "Model loading took %.4f GiB memory and %.6f seconds",
             self.model_memory_usage / GiB_bytes,
             time_after_load - time_before_load,
             scope="local",