---
license: apache-2.0
pipeline_tag: text-generation
tags:
- executorch
library_name: executorch
---

# smolLm-2

This repository hosts the **smolLm-2** 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 |
| --- | --- | --- |
| `135m/mlx/smollm2_135m_mlx_int8.pte` | mlx | 8w |
| `135m/xnnpack/smollm2_135m_xnnpack_8da8w.pte` | xnnpack | 8da8w |
| `1_7b/mlx/smollm2_1_7b_mlx_int8.pte` | mlx | 8w |
| `1_7b/xnnpack/smollm2_1_7b_xnnpack_8da8w.pte` | xnnpack | 8da8w |
| `360m/mlx/smollm2_360m_mlx_int8.pte` | mlx | 8w |
| `360m/xnnpack/smollm2_360m_xnnpack_8da8w.pte` | xnnpack | 8da8w |

## Repository structure

```
135m/mlx/config.json                         1.3 kB
135m/mlx/smollm2_135m_mlx_int8.pte           187 MB
135m/xnnpack/config.json                     1.3 kB
135m/xnnpack/smollm2_135m_xnnpack_8da8w.pte  158 MB
1_7b/mlx/config.json                         1.3 kB
1_7b/mlx/smollm2_1_7b_mlx_int8.pte           1.8 GB
1_7b/xnnpack/config.json                     1.3 kB
1_7b/xnnpack/smollm2_1_7b_xnnpack_8da8w.pte  1.7 GB
360m/mlx/config.json                         1.3 kB
360m/mlx/smollm2_360m_mlx_int8.pte           446 MB
360m/xnnpack/config.json                     1.3 kB
360m/xnnpack/smollm2_360m_xnnpack_8da8w.pte  393 MB
config.json                                  30 B
tokenizer.json                               2.0 MB
tokenizer_config.json                        3.7 kB
```

## 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.