diff --git a/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md b/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md
index 6bd48e87..2993ba0a 100644
--- a/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md
+++ b/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md
@@ -113,6 +113,14 @@ Please refer to [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Overvie
 
          ./run-arc.sh
 
+   .. tab:: Intel iGPU
+
+      For Intel iGPU, we recommend:
+
+      .. code-block:: bash
+
+         ./run-igpu.sh
+
    .. tab:: Intel Data Center GPU Max
 
       Please note that you need to run ``conda install -c conda-forge -y gperftools=2.10`` before running the benchmark script on Intel Data Center GPU Max Series.
diff --git a/python/llm/dev/benchmark/all-in-one/run-igpu.sh b/python/llm/dev/benchmark/all-in-one/run-igpu.sh
new file mode 100644
index 00000000..7f884196
--- /dev/null
+++ b/python/llm/dev/benchmark/all-in-one/run-igpu.sh
@@ -0,0 +1,6 @@
+source /opt/intel/oneapi/setvars.sh
+ 
+export SYCL_CACHE_PERSISTENT=1
+export BIGDL_LLM_XMX_DISABLED=1
+ 
+python run.py # make sure config YAML file