diff --git a/backend/python/exllama/Makefile b/backend/python/exllama/Makefile
index 52a180ae..f3938b13 100644
--- a/backend/python/exllama/Makefile
+++ b/backend/python/exllama/Makefile
@@ -8,3 +8,6 @@ run:
 	@echo "Running exllama..."
 	bash run.sh
 	@echo "exllama run."
+
+test:
+	bash test.sh
\ No newline at end of file
diff --git a/backend/python/exllama/test.py b/backend/python/exllama/test.py
new file mode 100644
index 00000000..4f909487
--- /dev/null
+++ b/backend/python/exllama/test.py
@@ -0,0 +1,63 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "exllama.py", "--addr", "localhost:50051"])
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.kill()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        time.sleep(10)
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.Health(backend_pb2.HealthMessage())
+                self.assertEqual(response.message, b'OK')
+        except Exception as err:
+            print(err)
+            self.fail("Server failed to start")
+        finally:
+            self.tearDown()
+
+    def test_load_model(self):
+        """
+        This method tests if the model is loaded successfully
+        """
+        time.sleep(10)
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(Model="iambestfeed/open_llama_3b_4bit_128g"))
+                self.assertTrue(response.success)
+                self.assertEqual(response.message, "Model loaded successfully")
+        except Exception as err:
+            print(err)
+            self.fail("LoadModel service failed")
+        finally:
+            self.tearDown()
diff --git a/backend/python/exllama/test.sh b/backend/python/exllama/test.sh
new file mode 100644
index 00000000..072fb85b
--- /dev/null
+++ b/backend/python/exllama/test.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+
+##
+## A bash script wrapper that runs the diffusers server with conda
+
+export PATH=$PATH:/opt/conda/bin
+
+# Activate conda environment
+source activate transformers
+
+# get the directory where the bash script is located
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+
+python -m unittest $DIR/test.py
\ No newline at end of file