diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 7264b7f..001c6c6 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -2,7 +2,7 @@
 files: ""
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.3.0
+    rev: v5.0.0
     hooks:
       - id: check-ast
       - id: check-toml
@@ -47,6 +47,6 @@ repos:
     hooks:
       - id: nbstripout
   - repo: https://github.com/hadialqattan/pycln # remove unused import
-    rev: v2.3.0
+    rev: v2.4.0
     hooks:
       - id: pycln
diff --git a/README.md b/README.md
index 57a2fe3..f9a4c86 100644
--- a/README.md
+++ b/README.md
@@ -18,6 +18,8 @@
 
 ## Requirements
 
+### CUDA 12
+
 For **local inference**, ensure that you have CUDA 12 and cuDNN 9 installed, as they are required for onnxruntime version 1.20.1.
 
 To install cuDNN 9:
@@ -26,8 +28,14 @@ To install cuDNN 9:
 apt-get -y install cudnn9-cuda-12
 ```
 
+### (Optional) TensorRT
+
 To perform inference using TensorRT, ensure you have TensorRT version 10.5 installed.
 
+```bash
+sudo apt-get install tensorrt
+```
+
 # Install
 
 Nvidia GPU:
diff --git a/notebooks/playground.ipynb b/notebooks/playground.ipynb
index 0d54d04..817d75c 100644
--- a/notebooks/playground.ipynb
+++ b/notebooks/playground.ipynb
@@ -79,28 +79,48 @@
     "We will load a model, deploy it locally, and then run inference on a sample image.\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Available Runtime Types"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from focoos.ports import RuntimeTypes\n",
     "\n",
-    "# os.environ[\"RUNTIME_TYPE\"] = \"onnx_trt16\"\n",
-    "from focoos import Focoos, DEV_API_URL\n",
-    "from focoos.config import FOCOOS_CONFIG\n",
+    "for runtime_type in RuntimeTypes:\n",
+    "    print(runtime_type)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### OnnxRuntime With CUDA (focoos_object365)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
     "import os\n",
     "from pprint import pprint\n",
     "from supervision import plot_image\n",
     "\n",
-    "print(FOCOOS_CONFIG)\n",
     "focoos = Focoos(\n",
     "    api_key=os.getenv(\"FOCOOS_API_KEY\"),\n",
-    "    host_url=DEV_API_URL,\n",
     ")\n",
     "image_path = \"./assets/ade_val_034.jpg\"\n",
-    "model_ref = \"focoos_rtdetr\"\n",
+    "model_ref = \"focoos_object365\"\n",
     "\n",
     "\n",
     "model = focoos.get_local_model(model_ref)\n",
@@ -115,6 +135,47 @@
     "plot_image(preview)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### OnnxRuntime With TensorRT (FP16) (focoos_object365)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from focoos import Focoos\n",
+    "import os\n",
+    "from pprint import pprint\n",
+    "from supervision import plot_image\n",
+    "\n",
+    "from focoos.ports import RuntimeTypes\n",
+    "\n",
+    "focoos = Focoos(\n",
+    "    api_key=os.getenv(\"FOCOOS_API_KEY\"),\n",
+    ")\n",
+    "image_path = \"./assets/ade_val_034.jpg\"\n",
+    "model_ref = \"focoos_object365\"\n",
+    "\n",
+    "\n",
+    "model = focoos.get_local_model(model_ref, runtime_type=RuntimeTypes.ONNX_TRT16)\n",
+    "\n",
+    "latency = model.benchmark(iterations=10, size=640)\n",
+    "pprint(latency)\n",
+    "# pprint(latency)\n",
+    "output, preview = model.infer(image_path, threshold=0.3, annotate=True)\n",
+    "pprint(output.detections)\n",
+    "pprint(output.latency)\n",
+    "\n",
+    "plot_image(preview)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},