qwen-3.5
This repository hosts the qwen-3.5 models exported for the
React Native ExecuTorch
library as ExecuTorch .pte programs, ready to run on device.
Variants
| Path | Backend | Precision | Context length |
|---|---|---|---|
0_8b/xnnpack/qwen_3_5_0_8b_xnnpack_8da4w.pte | xnnpack | 8da4w | 2,048 |
2b/xnnpack/qwen_3_5_2b_xnnpack_8da4w.pte | xnnpack | 8da4w | 2,048 |
vl_0_8b/xnnpack/qwen_3_5_vl_0_8b_xnnpack_8da4w.pte | xnnpack | 8da4w | 2,048 |
vl_2b/xnnpack/qwen_3_5_vl_2b_xnnpack_8da4w.pte | xnnpack | 8da4w | 2,048 |
Repository structure
0_8b/tokenizer.json 12.2 MiB
0_8b/tokenizer_config.json 14.0 KiB
0_8b/xnnpack/config.json 1.4 KiB
0_8b/xnnpack/qwen_3_5_0_8b_xnnpack_8da4w.pte 1.3 GiB
2b/tokenizer.json 12.2 MiB
2b/tokenizer_config.json 14.0 KiB
2b/xnnpack/config.json 1.4 KiB
2b/xnnpack/qwen_3_5_2b_xnnpack_8da4w.pte 2.8 GiB
config.json 30 B
vl_0_8b/tokenizer.json 12.2 MiB
vl_0_8b/tokenizer_config.json 14.0 KiB
vl_0_8b/xnnpack/config.json 1.2 KiB
vl_0_8b/xnnpack/qwen_3_5_vl_0_8b_xnnpack_8da4w.pte 1.7 GiB
vl_2b/tokenizer.json 12.2 MiB
vl_2b/tokenizer_config.json 14.0 KiB
vl_2b/xnnpack/config.json 1.1 KiB
vl_2b/xnnpack/qwen_3_5_vl_2b_xnnpack_8da4w.pte 4.0 GiB
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.