diff --git a/docs/docs/install/environment-variables.md b/docs/docs/install/environment-variables.md
index a33afd4f50..4193cc971c 100644
--- a/docs/docs/install/environment-variables.md
+++ b/docs/docs/install/environment-variables.md
@@ -167,9 +167,7 @@ Redis (Sentinel) URL example JSON before encoding:
 | `MACHINE_LEARNING_DEVICE_IDS`<sup>\*4</sup>               | Device IDs to use in multi-GPU environments                                                         |               `0`               | machine learning |
 | `MACHINE_LEARNING_MAX_BATCH_SIZE__FACIAL_RECOGNITION`     | Set the maximum number of faces that will be processed at once by the facial recognition model      |  None (`1` if using OpenVINO)   | machine learning |
 | `MACHINE_LEARNING_RKNN`                                   | Enable RKNN hardware acceleration if supported                                                      |             `True`              | machine learning |
-| `MACHINE_LEARNING_RKNN_TEXTUAL_THREADS`                   | How many threads of RKNN runtime should be spinned up while infrencing textual model.               |               `1`               | machine learning |
-| `MACHINE_LEARNING_RKNN_VISUAL_THREADS`                    | How many threads of RKNN runtime should be spinned up while infrencing visual model.                |               `1`               | machine learning |
-| `MACHINE_LEARNING_RKNN_FACIAL_THREADS`                    | How many threads of RKNN runtime should be spinned up while infrencing facial model.                |               `1`               | machine learning |
+| `MACHINE_LEARNING_RKNN_THREADS`                   | How many threads of RKNN runtime should be spinned up while inferencing.               |               `1`               | machine learning |
 
 \*1: It is recommended to begin with this parameter when changing the concurrency levels of the machine learning service and then tune the other ones.
 
diff --git a/machine-learning/app/config.py b/machine-learning/app/config.py
index 2782b82b45..932e12a230 100644
--- a/machine-learning/app/config.py
+++ b/machine-learning/app/config.py
@@ -45,9 +45,7 @@ class Settings(BaseSettings):
     ann_fp16_turbo: bool = False
     ann_tuning_level: int = 2
     rknn: bool = True
-    rknn_textual_threads: int = 1
-    rknn_visual_threads: int = 1
-    rknn_facial_detection_threads: int = 1
+    rknn_threads: int = 1
     preload: PreloadModelData | None = None
     max_batch_size: MaxBatchSize | None = None
 
diff --git a/machine-learning/app/sessions/rknn.py b/machine-learning/app/sessions/rknn.py
index fd79884be6..0ad3b7d52b 100644
--- a/machine-learning/app/sessions/rknn.py
+++ b/machine-learning/app/sessions/rknn.py
@@ -24,12 +24,7 @@ class RknnSession:
         self.model_path = Path(str(model_path).replace("model", soc_name))
         self.ort_model_path = Path(str(self.model_path).replace(f"{soc_name}.rknn", "model.onnx"))
 
-        if "textual" in str(self.model_path):
-            self.tpe = settings.rknn_textual_threads
-        elif "visual" in str(self.model_path):
-            self.tpe = settings.rknn_visual_threads
-        else:
-            self.tpe = settings.rknn_facial_detection_threads
+        self.tpe = settings.rknn_threads
 
         log.info(f"Loading RKNN model from {self.model_path} with {self.tpe} threads.")
         self.rknnpool = RknnPoolExecutor(rknnModel=self.model_path.as_posix(), tpes=self.tpe, func=runInfrence)