diff --git a/website/docs/installation/apple.md b/website/docs/installation/apple.md
index ff8bdd27254e..fe9d71d103a8 100644
--- a/website/docs/installation/apple.md
+++ b/website/docs/installation/apple.md
@@ -11,7 +11,7 @@ Thanks to Apple's Accelerate and CoreML frameworks, we can now run Tabby on edge
 brew install tabbyml/tabby/tabby
 
 # Start server with StarCoder-1B
-tabby serve --device metal --model StarCoder-1B
+tabby serve --device metal --model StarCoder-1B --no-webserver
 ```
 
 The compute power of M1/M2 is limited and is likely to be sufficient only for individual usage. If you require a shared instance for a team, we recommend considering Docker hosting with CUDA or ROCm. You can find more information about Docker [here](../docker).
diff --git a/website/docs/installation/docker-compose.mdx b/website/docs/installation/docker-compose.mdx
index 97f348f8db33..2ee164895164 100644
--- a/website/docs/installation/docker-compose.mdx
+++ b/website/docs/installation/docker-compose.mdx
@@ -22,7 +22,7 @@ services:
   tabby:
     restart: always
     image: tabbyml/tabby
-    command: serve --model StarCoder-1B --device cuda
+    command: serve --model StarCoder-1B --device cuda --no-webserver
     volumes:
       - "$HOME/.tabby:/data"
     ports:
@@ -47,7 +47,7 @@ services:
     restart: always
     image: tabbyml/tabby
     entrypoint: /opt/tabby/bin/tabby-cpu
-    command: serve --model StarCoder-1B
+    command: serve --model StarCoder-1B --no-webserver
     volumes:
       - "$HOME/.tabby:/data"
     ports:
diff --git a/website/docs/installation/docker.mdx b/website/docs/installation/docker.mdx
index 4ff5aa3f7cd1..62c51fc5eab0 100644
--- a/website/docs/installation/docker.mdx
+++ b/website/docs/installation/docker.mdx
@@ -19,7 +19,7 @@ import TabItem from '@theme/TabItem';
   ```bash title="run.sh"
   docker run -it --gpus all \
     -p 8080:8080 -v $HOME/.tabby:/data \
-    tabbyml/tabby serve --model StarCoder-1B --device cuda
+    tabbyml/tabby serve --model StarCoder-1B --device cuda --no-webserver
   ```
 
   </TabItem>
@@ -28,7 +28,7 @@ import TabItem from '@theme/TabItem';
   ```bash title="run.sh"
   docker run --entrypoint /opt/tabby/bin/tabby-cpu -it \
     -p 8080:8080 -v $HOME/.tabby:/data \
-    tabbyml/tabby serve --model StarCoder-1B
+    tabbyml/tabby serve --model StarCoder-1B --no-webserver
   ```
 
   </TabItem>
diff --git a/website/docs/installation/modal/app.py b/website/docs/installation/modal/app.py
index d305635b7c4a..fda968557565 100644
--- a/website/docs/installation/modal/app.py
+++ b/website/docs/installation/modal/app.py
@@ -60,6 +60,7 @@ def app():
             "cuda",
             "--parallelism",
             "4",
+            "--no-webserver",
         ]
     )
 
diff --git a/website/docs/installation/modal/index.md b/website/docs/installation/modal/index.md
index 1fff6396b9db..ee471c717ba8 100644
--- a/website/docs/installation/modal/index.md
+++ b/website/docs/installation/modal/index.md
@@ -103,6 +103,7 @@ def app():
             "8000",
             "--device",
             "cuda",
+            "--no-webserver",
         ]
     )
 
diff --git a/website/docs/installation/skypilot/index.md b/website/docs/installation/skypilot/index.md
index d596b84c6c2d..0ee1fc181619 100644
--- a/website/docs/installation/skypilot/index.md
+++ b/website/docs/installation/skypilot/index.md
@@ -35,7 +35,7 @@ Finally, we define the command line that actually initiates the container job:
 run: |
   docker run --gpus all -p 8080:8080 -v ~/.tabby:/data \
     tabbyml/tabby \
-    serve --model TabbyML/StarCoder-1B --device cuda
+    serve --model TabbyML/StarCoder-1B --device cuda --no-webserver
 ```
 
 ## Launch the service
diff --git a/website/docs/installation/windows/index.mdx b/website/docs/installation/windows/index.mdx
index a2de87ef6257..f84b2c7d62af 100644
--- a/website/docs/installation/windows/index.mdx
+++ b/website/docs/installation/windows/index.mdx
@@ -25,7 +25,7 @@ nvcc --version
 ## 3. Running Tabby locally
 Open a command prompt or PowerShell window in the directory where you downloaded the Tabby executable. Run the following command:
 ```
-.\tabby_x86_64-windows-msvc-cuda117.exe serve --model StarCoder-1B --device cuda
+.\tabby_x86_64-windows-msvc-cuda117.exe serve --model StarCoder-1B --device cuda --no-webserver
 ```
 You should see the following output if the command runs successfully:
 ![Windows running output](./status.png)