diff --git a/benchmarking/testserver/models/text-model/model-settings.json b/benchmarking/testserver/models/text-model/model-settings.json
deleted file mode 100644
index 12eed8415..000000000
--- a/benchmarking/testserver/models/text-model/model-settings.json
+++ /dev/null
@@ -1,22 +0,0 @@
-{
-  "name": "text-model",
-
-  "implementation": "text_model.TextModel",
-  
-  "versions": ["text-model/v1.2.3"],
-  "platform": "mlserver",
-  "inputs": [
-    {
-      "datatype": "BYTES",
-      "name": "prompt",
-      "shape": [1]
-    }
-  ],
-  "outputs": [
-    {
-      "datatype": "BYTES",
-      "name": "output",
-      "shape": [1]
-    }
-  ]
-}
diff --git a/benchmarking/testserver/models/text-model/settings.json b/benchmarking/testserver/models/text-model/settings.json
deleted file mode 100644
index b5af111b4..000000000
--- a/benchmarking/testserver/models/text-model/settings.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
-  "debug": false,
-  "parallel_workers": 0,
-  "gzip_enabled": false,
-  "metrics_endpoint": null
-}
diff --git a/benchmarking/testserver/models/text-model/text_model.py b/benchmarking/testserver/models/text-model/text_model.py
deleted file mode 100644
index 4475b3c92..000000000
--- a/benchmarking/testserver/models/text-model/text_model.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import asyncio
-from typing import AsyncIterator
-from mlserver import MLModel
-from mlserver.types import InferenceRequest, InferenceResponse
-from mlserver.codecs import StringCodec
-
-
-class TextModel(MLModel):
-
-    async def predict(self, payload: InferenceRequest) -> InferenceResponse:
-        text = StringCodec.decode_input(payload.inputs[0])[0]
-        return InferenceResponse(
-            model_name=self._settings.name,
-            outputs=[
-                StringCodec.encode_output(
-                    name="output",
-                    payload=[text],
-                    use_bytes=True,
-                ),
-            ],
-        )
-
-    async def predict_stream(
-        self, payloads: AsyncIterator[InferenceRequest]
-    ) -> AsyncIterator[InferenceResponse]:
-        payload = [_ async for _ in payloads][0]
-        text = StringCodec.decode_input(payload.inputs[0])[0]
-        words = text.split(" ")
-
-        split_text = []
-        for i, word in enumerate(words):
-            split_text.append(word if i == 0 else " " + word)
-
-        for word in split_text:
-            await asyncio.sleep(0.5)
-            yield InferenceResponse(
-                model_name=self._settings.name,
-                outputs=[
-                    StringCodec.encode_output(
-                        name="output",
-                        payload=[word],
-                        use_bytes=True,
-                    ),
-                ],
-            )