# Supported AI accelerators

The Nx AI Manager has integrated several runtimes allowing to benefit from hardware acceleration to run the deployed models across different AI Accelerators.

The following tables contain a compiled list of supported AI Accelerators, their support level and the required software configuration:

### Fully supported

| Support Level | AI Accelerator                                                                   | CPU Architecture | API/driver version              | Operating System       |
| ------------- | -------------------------------------------------------------------------------- | ---------------- | ------------------------------- | ---------------------- |
| Full support  | CPU                                                                              | aarch64, x86\_64 | -                               | Ubuntu 20+ and Windows |
| Full support  | [Intel CPU](/nx-ai-manager-v6.1.2/ai-accelerators-support/intel-support.md)      | x86\_64          | OpenVino                        | Ubuntu 22+ and Windows |
| Full support  | [NVIDIA dGPU](/nx-ai-manager-v6.1.2/ai-accelerators-support/nvidia-support.md)   | x86\_64          | CUDA 11, CUDA 12, CUDA 13       | Ubuntu 20+ and Windows |
| Full support  | [NVIDIA dGPU](/nx-ai-manager-v6.1.2/ai-accelerators-support/nvidia-support.md)   | aarch64          | CUDA 13                         | Ubuntu 24.04           |
| Full support  | [NVIDIA Jetson](/nx-ai-manager-v6.1.2/ai-accelerators-support/nvidia-support.md) | aarch64          | JetPack 5, JetPack 6, JetPack 7 | Ubuntu 20+             |

### Experimental

| Support Level | AI Accelerator                                                                         | CPU Architecture | API/driver version                | Operating System       |
| ------------- | -------------------------------------------------------------------------------------- | ---------------- | --------------------------------- | ---------------------- |
| Experimental  | [Intel GPU/NPU](/nx-ai-manager-v6.1.2/ai-accelerators-support/intel-support.md)        | x86\_64          | OpenVino                          | Ubuntu 22+ and Windows |
| Experimental  | [DEEPX DX-M1](/nx-ai-manager-v6.1.2/ai-accelerators-support/advanced/deepx-support.md) | aarch64, x86\_64 | <p>DXRT v3.0.0<br>DXRT v3.1.0</p> | Ubuntu 20+             |
| Experimental  | [DEEPX DX-H1](/nx-ai-manager-v6.1.2/ai-accelerators-support/advanced/deepx-support.md) | aarch64, x86\_64 | <p>DXRT v3.0.0<br>DXRT v3.1.0</p> | Ubuntu 20+             |
| Experimental  | [Hailo-8](/nx-ai-manager-v6.1.2/ai-accelerators-support/advanced/hailo-support.md)     | x86\_64, aarch64 | 4.18.0, 4.19.0, 4.20.0            | Ubuntu 20+             |
| Experimental  | [Hailo-8L](/nx-ai-manager-v6.1.2/ai-accelerators-support/advanced/hailo-support.md)    | x86\_64, aarch64 | 4.18.0, 4.19.0, 4.20.0            | Ubuntu 20+             |
| Experimental  | EdgeCortix SAKURA-II                                                                   | x86\_64          | MERA 2.5                          | Ubuntu 22.04           |
| Experimental  | MemryX MX3                                                                             | x86\_64          | Driver 2.1.0                      | Ubuntu 22.04           |

### In the works

| Support Level | AI Accelerator | CPU Architecture | API/driver version | Operating System |
| ------------- | -------------- | ---------------- | ------------------ | ---------------- |
| Coming Soon   | Axelera Metis  | x86\_64          | TBD                | Ubuntu           |
| Coming Soon   | SiMA           | x86\_64          | TBD                | Ubuntu           |


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://nx.docs.scailable.net/nx-ai-manager-v6.1.2/ai-accelerators-support/supported-ai-accelerators.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.