---
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 | Context length |
| --- | --- | --- | --- |
| `135m/mlx/smollm2_135m_mlx_int8.pte` | mlx | int8 | 16,384 |
| `135m/xnnpack/smollm2_135m_xnnpack_8da8w.pte` | xnnpack | 8da8w | 16,384 |
| `1_7b/mlx/smollm2_1_7b_mlx_int8.pte` | mlx | int8 | 2,048 |
| `1_7b/xnnpack/smollm2_1_7b_xnnpack_8da8w.pte` | xnnpack | 8da8w | 2,048 |
| `360m/mlx/smollm2_360m_mlx_int8.pte` | mlx | int8 | 16,384 |
| `360m/xnnpack/smollm2_360m_xnnpack_8da8w.pte` | xnnpack | 8da8w | 16,384 |



## Repository structure

```
135m/mlx/config.json                         1.3 KiB
135m/mlx/smollm2_135m_mlx_int8.pte           187 MiB
135m/xnnpack/config.json                     1.3 KiB
135m/xnnpack/smollm2_135m_xnnpack_8da8w.pte  165 MiB
1_7b/mlx/config.json                         1.3 KiB
1_7b/mlx/smollm2_1_7b_mlx_int8.pte           1.8 GiB
1_7b/xnnpack/config.json                     1.3 KiB
1_7b/xnnpack/smollm2_1_7b_xnnpack_8da8w.pte  1.7 GiB
360m/mlx/config.json                         1.3 KiB
360m/mlx/smollm2_360m_mlx_int8.pte           446 MiB
360m/xnnpack/config.json                     1.3 KiB
360m/xnnpack/smollm2_360m_xnnpack_8da8w.pte  400 MiB
config.json                                  30 B
tokenizer.json                               2.0 MiB
tokenizer_config.json                        3.7 KiB
```

## 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.