qwen-2.5

This repository hosts the qwen-2.5 models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Variants

Repository structure

0_5b/mlx/config.json                          1.3 kB
0_5b/mlx/qwen_2_5_0_5b_mlx_int4.pte           510 MB
0_5b/xnnpack/config.json                      2.3 kB
0_5b/xnnpack/qwen_2_5_0_5b_xnnpack_8da4w.pte  398 MB
0_5b/xnnpack/qwen_2_5_0_5b_xnnpack_bf16.pte   944 MB
1_5b/mlx/config.json                          1.3 kB
1_5b/mlx/qwen_2_5_1_5b_mlx_int4.pte           1.2 GB
1_5b/xnnpack/config.json                      2.3 kB
1_5b/xnnpack/qwen_2_5_1_5b_xnnpack_8da4w.pte  1.1 GB
1_5b/xnnpack/qwen_2_5_1_5b_xnnpack_bf16.pte   2.9 GB
3b/mlx/config.json                            1.3 kB
3b/mlx/qwen_2_5_3b_mlx_int4.pte               2.1 GB
3b/xnnpack/config.json                        2.3 kB
3b/xnnpack/qwen_2_5_3b_xnnpack_8da4w.pte      1.9 GB
3b/xnnpack/qwen_2_5_3b_xnnpack_bf16.pte       5.8 GB
config.json                                   30 B
tokenizer.json                                6.7 MB
tokenizer_config.json                         7.1 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.

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