diff --git a/docs/docs/install/environment-variables.md b/docs/docs/install/environment-variables.md
index 64a3078fc8385..3a0db9928d5c6 100644
--- a/docs/docs/install/environment-variables.md
+++ b/docs/docs/install/environment-variables.md
@@ -155,18 +155,18 @@ Redis (Sentinel) URL example JSON before encoding:
 
 ## Machine Learning
 
-| Variable                                         | Description                                                          |       Default       | Containers       |
-| :----------------------------------------------- | :------------------------------------------------------------------- | :-----------------: | :--------------- |
-| `MACHINE_LEARNING_MODEL_TTL`                     | Inactivity time (s) before a model is unloaded (disabled if \<= 0)   |        `300`        | machine learning |
-| `MACHINE_LEARNING_MODEL_TTL_POLL_S`              | Interval (s) between checks for the model TTL (disabled if \<= 0)    |        `10`         | machine learning |
-| `MACHINE_LEARNING_CACHE_FOLDER`                  | Directory where models are downloaded                                |      `/cache`       | machine learning |
-| `MACHINE_LEARNING_REQUEST_THREADS`<sup>\*1</sup> | Thread count of the request thread pool (disabled if \<= 0)          | number of CPU cores | machine learning |
-| `MACHINE_LEARNING_MODEL_INTER_OP_THREADS`        | Number of parallel model operations                                  |         `1`         | machine learning |
-| `MACHINE_LEARNING_MODEL_INTRA_OP_THREADS`        | Number of threads for each model operation                           |         `2`         | machine learning |
-| `MACHINE_LEARNING_WORKERS`<sup>\*2</sup>         | Number of worker processes to spawn                                  |         `1`         | machine learning |
-| `MACHINE_LEARNING_WORKER_TIMEOUT`                | Maximum time (s) of unresponsiveness before a worker is killed       |        `120`        | machine learning |
-| `MACHINE_LEARNING_PRELOAD__CLIP`                 | Name of a CLIP model to be preloaded and kept in cache               |                     | machine learning |
-| `MACHINE_LEARNING_PRELOAD__FACIAL_RECOGNITION`   | Name of a facial recognition model to be preloaded and kept in cache |                     | machine learning |
+| Variable                                         | Description                                                          |                Default                | Containers       |
+| :----------------------------------------------- | :------------------------------------------------------------------- | :-----------------------------------: | :--------------- |
+| `MACHINE_LEARNING_MODEL_TTL`                     | Inactivity time (s) before a model is unloaded (disabled if \<= 0)   |                 `300`                 | machine learning |
+| `MACHINE_LEARNING_MODEL_TTL_POLL_S`              | Interval (s) between checks for the model TTL (disabled if \<= 0)    |                 `10`                  | machine learning |
+| `MACHINE_LEARNING_CACHE_FOLDER`                  | Directory where models are downloaded                                |               `/cache`                | machine learning |
+| `MACHINE_LEARNING_REQUEST_THREADS`<sup>\*1</sup> | Thread count of the request thread pool (disabled if \<= 0)          |          number of CPU cores          | machine learning |
+| `MACHINE_LEARNING_MODEL_INTER_OP_THREADS`        | Number of parallel model operations                                  |                  `1`                  | machine learning |
+| `MACHINE_LEARNING_MODEL_INTRA_OP_THREADS`        | Number of threads for each model operation                           |                  `2`                  | machine learning |
+| `MACHINE_LEARNING_WORKERS`<sup>\*2</sup>         | Number of worker processes to spawn                                  |                  `1`                  | machine learning |
+| `MACHINE_LEARNING_WORKER_TIMEOUT`                | Maximum time (s) of unresponsiveness before a worker is killed       | `120` (`300` if using OpenVINO image) | machine learning |
+| `MACHINE_LEARNING_PRELOAD__CLIP`                 | Name of a CLIP model to be preloaded and kept in cache               |                                       | machine learning |
+| `MACHINE_LEARNING_PRELOAD__FACIAL_RECOGNITION`   | Name of a facial recognition model to be preloaded and kept in cache |                                       | 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/Dockerfile b/machine-learning/Dockerfile
index 1aea125a1460f..92d4850f383e7 100644
--- a/machine-learning/Dockerfile
+++ b/machine-learning/Dockerfile
@@ -77,6 +77,7 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/*
 
 WORKDIR /usr/src/app
+ARG DEVICE
 ENV TRANSFORMERS_CACHE=/cache \
     PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
diff --git a/machine-learning/start.sh b/machine-learning/start.sh
index 9d0a505c0c56c..7a35c1fd51991 100755
--- a/machine-learning/start.sh
+++ b/machine-learning/start.sh
@@ -5,12 +5,13 @@ lib_path="/usr/lib/$(arch)-linux-gnu/libmimalloc.so.2"
 if ! [ "$DEVICE" = "openvino" ]; then
 	export LD_PRELOAD="$lib_path"
 	export LD_BIND_NOW=1
+	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=120}"
+else
+	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=300}"
 fi
 
 : "${IMMICH_HOST:=[::]}"
 : "${IMMICH_PORT:=3003}"
-: "${MACHINE_LEARNING_WORKERS:=1}"
-: "${MACHINE_LEARNING_WORKER_TIMEOUT:=120}"
 
 gunicorn app.main:app \
 	-k app.config.CustomUvicornWorker \