| --- |
| license: mit |
| pipeline_tag: text-generation |
| tags: |
| - executorch |
| library_name: executorch |
| --- |
| |
| # phi-4-mini |
|
|
| This repository hosts the **phi-4-mini** models exported for the |
| [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) |
| library as ExecuTorch `.pte` programs, ready to run on device. |
|
|
| ## Variants |
|
|
| | Path | Backend | Precision | |
| | --- | --- | --- | |
| | `mlx/phi_4_mini_mlx_int4.pte` | mlx | 4w | |
| | `xnnpack/phi_4_mini_xnnpack_bf16.pte` | xnnpack | bf16 | |
| | `xnnpack/phi_4_mini_xnnpack_8da4w.pte` | xnnpack | 8da4w | |
|
|
| ## Repository structure |
|
|
| ``` |
| config.json 32 B |
| mlx/config.json 1.3 kB |
| mlx/phi_4_mini_mlx_int4.pte 3.0 GB |
| tokenizer.json 14.8 MB |
| tokenizer_config.json 2.9 kB |
| xnnpack/config.json 2.3 kB |
| xnnpack/phi_4_mini_xnnpack_8da4w.pte 2.6 GB |
| xnnpack/phi_4_mini_xnnpack_bf16.pte 7.1 GB |
| ``` |
|
|
| ## Compatibility |
|
|
| These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch |
| gives no forward compatibility guarantee, so an older runtime may fail to load |
| them. |
|
|
| To use them in React Native ExecuTorch, pass the model constant shipped in the |
| library's model registry to the corresponding task pipeline. See the |
| [documentation](https://docs.swmansion.com/react-native-executorch/docs/fundamentals/downloading-models). |
|
|
| To load these files in your own ExecuTorch runtime, read the |
| [compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md) |
| first. |
|
|
