# nsx-tflite-micro

<!-- nsx:facts -->
Thin NSX wrapper for the helia-rt TensorFlow Lite Micro runtime using reference kernels or standard Arm CMSIS-NN kernels.

- Type: Library / service
- Version: 0.1.0
- Project: nsx-tflite-micro
- Revision: v0.1.0
- Source: https://github.com/AmbiqAI/nsx-tflite-micro/tree/v0.1.0
- Capabilities: inference, tflm, machine_learning, profiling
<!-- /nsx:facts -->

## Add it to an app

```bash
nsx module add nsx-tflite-micro
```

## Capabilities

- inference
- tflm
- machine_learning
- profiling

## Use cases

- TFLM inference on Ambiq SoCs
- reference-versus-CMSIS-NN kernel comparisons
- helia-profiler runtime measurements

## Requires

- [`helia-rt-source`](https://ambiqai.github.io/neuralspotx/modules/helia-rt-source/)
- [`nsx-core`](https://ambiqai.github.io/neuralspotx/modules/nsx-core/)
- [`nsx-soc-hal`](https://ambiqai.github.io/neuralspotx/modules/nsx-soc-hal/)

## Optional dependencies

- [`arm-cmsis-nn`](https://ambiqai.github.io/neuralspotx/modules/arm-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`, `tflite`, `cmsis-nn`, `profiling`, `helia-profiler`

## Source

| Field | Value |
| --- | --- |
| Type | Library / service |
| Version | 0.1.0 |
| Project | nsx-tflite-micro |
| Revision | `v0.1.0` |
| Manifest | `modules/nsx-tflite-micro/nsx-module.yaml` |
| Repository | [nsx-tflite-micro](https://github.com/AmbiqAI/nsx-tflite-micro/tree/v0.1.0) |

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