Install on Windows

Windows Installer (x86)

You can run Roboflow Inference Server on your Windows machine using the native desktop app.

Simply download the latest Windows installer from the latest release on GitHub: View Latest Release and Download Installers on GitHub

Windows Installation Steps

Download the latest installer and run it to install Roboflow Inference
When the install is finished it will offer to launch the Inference server after the setup completes
To stop the inference server simply close the terminal window it opens
To start it again later, you can find Roboflow Inference in your Start Menu

Using Docker

First, you'll need to install Docker Desktop. Then, use the CLI to start the container.

pip install inference-cli
inference server start

Note

If the pip install command fails, you may need to install Python first. Once you have Python version 3.12, 3.11, or 3.10 on your machine, retry the command.

Manually Starting the Container

If you want more control of the container settings you can also start it manually.

The core CPU Docker image includes support for OpenVINO acceleration on x64 CPUs via onnxruntime. Heavy models like SAM2 and CogVLM may run too slowly (dozens of seconds per image) to be practical (and you should look into getting a CUDA-capable GPU if you want to use them).

The primary use-cases for CPU inference are processing still images (e.g. for NSFW classification of uploads or document verification) or infrequent sampling of frames on a video (e.g. for occupancy tracking of a parking lot).

To get started with CPU inference, use the roboflow/roboflow-inference-server-cpu:latest container.

docker run -d ^
    --name inference-server ^
    --read-only ^
    -p 9001:9001 ^
    --volume "%USERPROFILE%\.inference\cache:/tmp:rw" ^
    --security-opt="no-new-privileges" ^
    --cap-drop="ALL" ^
    --cap-add="NET_BIND_SERVICE" ^
    roboflow/roboflow-inference-server-cpu:latest

Docker Compose

If you are using Docker Compose for your application, the equivalent yaml is:

version: "3.9"

services:
  inference-server:
    container_name: inference-server
    image: roboflow/roboflow-inference-server-cpu:latest

    read_only: true
    ports:
      - "9001:9001"

    volumes:
      - "${USERPROFILE}/.inference/cache:/tmp:rw"

    security_opt:
      - no-new-privileges
    cap_drop:
      - ALL
    cap_add:
      - NET_BIND_SERVICE

Using Your New Server

See Using Your New Server for next steps.

Enterprise Considerations

A Helm Chart is available for enterprise cloud deployments. Enterprise networking solutions to support deployment in OT networks are also available upon request.

Roboflow also offers customized support and installation packages and a pre-configured Jetson-based edge device suitable for rapid prototyping. Contact our sales team if you're part of a large organization and interested in learning more.