---
license: other
license_name: qwen-research
license_link: LICENSE
base_model:
- Qwen/Qwen-Image-2.1
base_model_relation: quantized
pipeline_tag: text-to-image
library_name: mnn
tags:
- mnn
- android
- opencl
- int4
- qwen-image
---

# Qwen-Image-2.1 · MNN (int4) for Android

[Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1) converted to [MNN](https://github.com/alibaba/MNN)
for on-device **text-to-image and image editing** on Android at about 512×512 pixels (any aspect ratio with sides that
are multiples of 32, e.g. 512×512, 576×448, 608×416, 672×384), with the OpenCL GPU running the DiT.

Runtime, Android library and demo app: **[github.com/scsonic/libQwenImage21](https://github.com/scsonic/libQwenImage21)**

| Tested on | Snapdragon 8 Gen 2 (Adreno 740), 16 GB RAM, Android 13 |
|---|---|
| 512×512, 20 steps | ~490 s total (DiT ~19.7 s/step on OpenCL fp16) |

## Files

| Path | What | Size |
|---|---|---|
| `dit.mnn` + `.weight` | 7B single-stream DiT (32 blocks + norm_out/proj_out). Block linears int4 (block 32), small layers int8 | 4.5 GB |
| `txt_in.mnn`, `img_in.mnn` | text (int8) / latent (fp16) input projections | 36 MB |
| `vae_decoder.mnn` | VAE decoder, 64-ch latent → RGBA, fp16 weights, dynamic size | 0.5 GB |
| `vae_encoder.mnn` | VAE encoder for image editing, RGBA → normalized 64-ch latent, fp16 | 0.16 GB |
| `text_encoder/` | Qwen3-VL-8B-Instruct, MNN int4 (from [taobao-mnn/Qwen3-VL-8B-Instruct-MNN](https://huggingface.co/taobao-mnn/Qwen3-VL-8B-Instruct-MNN)). `te_config.json` runs it text-only; `te_vl_config.json` adds the vision tower (`visual.mnn`) for image editing. Both return the last decoder layer before the final norm | 5.4 GB |

Download:

```bash
hf download evankuo/Qwen-Image-2.1-MNN --local-dir qwen_image21
```

## How it was made

- **DiT**: taken from the GGUF **Q4_K** build ([leejet/Qwen-Image-2.1-GGUF](https://huggingface.co/leejet/Qwen-Image-2.1-GGUF)).
  Every Q4_K sub-block of 32 weights (`w = d·sc·q − dmin·m`) maps exactly onto MNN's asymmetric int4 with block 32,
  so the weights are copied without re-quantization (scales stored as fp16).
- **Text encoder**: Qwen-Image-2.1's `text_encoder` is byte-identical to Qwen3-VL-8B-Instruct, so the existing MNN
  export is reused unchanged.
- **VAE**: the residual stream is divided by 256 (exact, power of two) and RMSNorm pre-divides by max|x| so the decoder
  fits fp16 (it peaks at ~3.5e5 otherwise). The decoded image is unchanged.
- The pipeline caches the text K/V once per prompt (Qwen-Image-2.1's block-causal attention), so each denoising step
  only runs the 1024 image tokens.

Conversion scripts: `export/` in the GitHub repo.

## License

Derived from Qwen-Image-2.1 and released under the **Qwen Research License Agreement** (see `LICENSE`), i.e. for
research / non-commercial use under its terms. The text encoder weights come from Qwen3-VL-8B-Instruct (Apache-2.0).