software-mansion/react-native-executorch-qwen-3

qwen-3

This repository hosts the qwen-3 models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Variants

Path	Backend	Precision	Context length
0_6b/mlx/qwen_3_0_6b_mlx_int8.pte	mlx	int8	8,192
0_6b/xnnpack/qwen_3_0_6b_xnnpack_8da4w.pte	xnnpack	8da4w	8,192
1_7b/mlx/qwen_3_1_7b_mlx_int4.pte	mlx	int4	4,096
1_7b/xnnpack/qwen_3_1_7b_xnnpack_8da4w.pte	xnnpack	8da4w	4,096
4b/mlx/qwen_3_4b_mlx_int4.pte	mlx	int4	4,096
4b/xnnpack/qwen_3_4b_xnnpack_8da4w.pte	xnnpack	8da4w	4,096

Repository structure

0_6b/mlx/config.json                        1.3 KiB
0_6b/mlx/qwen_3_0_6b_mlx_int8.pte           883 MiB
0_6b/xnnpack/config.json                    1.3 KiB
0_6b/xnnpack/qwen_3_0_6b_xnnpack_8da4w.pte  494 MiB
1_7b/mlx/config.json                        1.3 KiB
1_7b/mlx/qwen_3_1_7b_mlx_int4.pte           1.4 GiB
1_7b/xnnpack/config.json                    1.3 KiB
1_7b/xnnpack/qwen_3_1_7b_xnnpack_8da4w.pte  1.2 GiB
4b/mlx/config.json                          1.3 KiB
4b/mlx/qwen_3_4b_mlx_int4.pte               2.7 GiB
4b/xnnpack/config.json                      1.3 KiB
4b/xnnpack/qwen_3_4b_xnnpack_8da4w.pte      2.5 GiB
config.json                                 28 B
tokenizer.json                              10.9 MiB
tokenizer_config.json                       8.2 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.

To load these files in your own ExecuTorch runtime, read the compatibility note first.