> For the complete documentation index, see [llms.txt](https://doc.faceplugin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.faceplugin.com/integration/deploy-and-host/hosting-requirements.md).

# Hosting requirements

Faceplugin hosting requirements. CPU, RAM, disk, ports, Docker shm-size, and OS notes for Face Recognition, Face Liveness, and ID Document server SDKs.

Use this page to size a host for Faceplugin **server** SDKs. Numbers match the public App README system requirement tables. Do not invent higher figures than those tables.

All shipping server products are **CPU only**. There is no `lib/gpu/` package in these apps.

**shm** means Docker shared memory (`--shm-size`). Document products need enough shm to unpack model packs such as `dcr.fpk`.

## Ports

| Product                            | API port | Gradio (host only) | Docker image                               | Role                                             |
| ---------------------------------- | -------: | -----------------: | ------------------------------------------ | ------------------------------------------------ |
| ID Document Recognition + Liveness |     8082 |               9002 | `faceplugin/document-reader`               | **Recommended** for OCR + authenticity           |
| Face Recognition + Liveness        |     8083 |               9003 | `faceplugin/face-recognition-liveness-sdk` | **Recommended** for match + face PAD             |
| Face Recognition (only)            |     8083 |               9003 | `faceplugin/face-recognition`              | Match only — no `/api/liveness`                  |
| Face Liveness (only)               |     8084 |               9004 | `faceplugin/face-liveness`                 | PAD only — use when you do not need match        |
| ID Document Liveness (only)        |     8086 |               9006 | `faceplugin/document-liveness`             | Authenticity only — use when you do not need OCR |

Gradio is for local demos. Do not expose it in production. See [Production deployment](/integration/deploy-and-host/production-deployment.md).

Prefer the **combined** Face and Document images for eKYC so you do not run separate recognition and liveness containers. Details: [Architecture](/integration/deploy-and-host/architecture.md).

## Per-product sizing

| Product                            | Min CPU                                    | Min RAM | Min disk | Recommended                    | OS notes                                                                                                       | Docker extras                                                                         |
| ---------------------------------- | ------------------------------------------ | ------- | -------- | ------------------------------ | -------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| Face Recognition + Liveness        | 2 cores                                    | 4 GB    | 4 GB     | 4 cores / 8 GB RAM / 8 GB disk | Docker: Ubuntu 22.04 / 24.04. Native Linux needs glibc **2.38+** (for example Ubuntu 24.04). Windows 10/11 x64 | `--shm-size=2gb --privileged`. On Linux mount `/etc/machine-id:ro`                    |
| Face Recognition (only)            | 2 cores                                    | 4 GB    | 4 GB     | 4 cores / 8 GB RAM / 8 GB disk | Same as combined                                                                                               | `--shm-size=2gb --privileged`. On Linux mount `/etc/machine-id:ro`                    |
| Face Liveness (only)               | 2 cores (Linux) / 4 cores (Windows README) | 4 GB    | 4 GB     | 4 cores / 8 GB RAM / 8 GB disk | Same Docker OS guidance as Face Recognition. Windows 10/11 x64                                                 | `--shm-size=1gb --privileged`. On Linux mount `/etc/machine-id:ro`                    |
| ID Document Recognition + Liveness | 2 cores                                    | 4 GB    | 4 GB     | 4 cores / 8 GB RAM / 8 GB disk | Ubuntu 20.04+ x86\_64; recommend 22.04 / 24.04. Windows 10/11 x64. CPU only                                    | `--shm-size=2gb` is **required**. `--privileged`. On Linux mount `/etc/machine-id:ro` |
| ID Document Liveness (only)        | 2 cores                                    | 4 GB    | 4 GB     | 4 cores / 8 GB RAM / 8 GB disk | Align with Document Reader Linux                                                                               | `--shm-size=2gb` is **required**. `--privileged`. On Linux mount `/etc/machine-id:ro` |

For a typical eKYC box, plan **two** containers: Document Reader (**8082**) + Face Recognition + Liveness (**8083**). Add RAM/CPU for each. Each container keeps its own `lib/cpu/` — do not mix product Drive folders. See [Architecture](/integration/deploy-and-host/architecture.md).

## Docker rules

* On **Docker Desktop** (macOS / Windows), omit the `/etc/machine-id` volume.
* On Linux Engine, mounting `/etc/machine-id` lets several containers on the same host share one machine code for licensing.
* A smaller `--shm-size` than required can crash Document Reader when `dcr.fpk` unpacks.
* Docker Hub images already include the runtime. You do not need Google Drive for Option A Hub pulls.

## Mobile devices

Mobile SDKs run on the phone. Prefer a **physical device** for camera work. Emulator cameras often stay black. See [Troubleshooting](/help/resources/troubleshooting.md).

This page does not invent phone RAM minimums beyond each platform README.

### Related documentation

* [Architecture](/integration/deploy-and-host/architecture.md) · [Production deployment](/integration/deploy-and-host/production-deployment.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://doc.faceplugin.com/integration/deploy-and-host/hosting-requirements.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.