# nsx-helia-rt

<!-- nsx:facts -->
Ambiq-optimized TensorFlow Lite for Microcontrollers (TFLM) runtime. Built from source against the nsx-cmsis-nn (ns-cmsis-nn >= 7.47.0) kernel module.

- Type: Algorithm
- Version: 2.2.1
- Project: helia-rt
- Revision: helia-rt-v2.2.1
- Source: https://github.com/AmbiqAI/helia-rt/tree/helia-rt-v2.2.1
- Capabilities: inference, tflm, machine_learning, litert
<!-- /nsx:facts -->

## Add it to an app

```bash
nsx module add nsx-helia-rt
```

## Capabilities

- inference
- tflm
- machine_learning
- litert

## Use cases

- on-device ML inference
- tflite model deployment on Ambiq SoCs
- keyword spotting and anomaly detection models

## Requires

- [`nsx-core`](https://ambiqai.github.io/neuralspotx/modules/nsx-core/)
- [`nsx-soc-hal`](https://ambiqai.github.io/neuralspotx/modules/nsx-soc-hal/)
- [`nsx-cmsis-nn`](https://ambiqai.github.io/neuralspotx/modules/nsx-cmsis-nn/)

## Compatibility

:::note[How compatibility is declared]
The boards, SoCs and toolchains listed here are the ones the module manifest declares.
That is the module author's statement of intent, not evidence from hardware. Confirm on your
own target before you depend on it.
:::

| Kind | Declared |
| --- | --- |
| Boards | * |
| SoCs | * |
| Toolchains | arm-none-eabi-gcc, armclang, atfe |

## Agent keywords

`tflm`, `tensorflow`, `inference`, `litert`, `machine_learning`, `helia-rt`, `helia_rt`, `tflite`

## Source

| Field | Value |
| --- | --- |
| Type | Algorithm |
| Version | 2.2.1 |
| Project | helia-rt |
| Revision | `helia-rt-v2.2.1` |
| Manifest | `modules/helia-rt/nsx/nsx-module.yaml` |
| Repository | [helia-rt](https://github.com/AmbiqAI/helia-rt/tree/helia-rt-v2.2.1) |

Back to the [module catalog](https://ambiqai.github.io/neuralspotx/modules/catalog/).