---
title: Qwen-Image-2.1-mflux-8bit
canonical_url: "https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-mflux-8bit"
md_url: "https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-mflux-8bit.md"
repository: OsaurusAI/Qwen-Image-2.1-mflux-8bit
last_updated: 2026-10-02
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2.1
base_model_relation: quantized
parameters: 2.0B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 236
stars: 0
tags:
  - text-to-image
  - image-to-image
  - image-editing
  - mflux
  - quantized
  - osaurus
  - non-commercial
  - research-only
---

# Qwen-Image-2.1-mflux-8bit

> Qwen-Image-2.1-mflux-8bit - OsaurusAI 在 ModelScope 开源的模型。# Research and evaluation use only — not for commercial use These weights are a quantized derivative of Qwen/Qwen-Image-2.1 and are distributed under the Qwen Research License Agreement (LICENSE). The…

OsaurusAI/Qwen-Image-2.1-mflux-8bit 是 ModelScope 魔搭社区上的 2.0B 参数text-to-image-synthesis模型，采用 other 许可，基于 Qwen/Qwen-Image-2.1 构建。

- **Repository**: OsaurusAI/Qwen-Image-2.1-mflux-8bit
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.0B
- **Base model**: Qwen/Qwen-Image-2.1
- **Tags**: text-to-image, image-to-image, image-editing, mflux, quantized, osaurus, non-commercial, research-only
- **Downloads**: 236
- **Stars**: 0
- **Last updated**: 2026-10-02

Source: https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-mflux-8bit

---

![Osaurus](osaurus-x-banner.png)

> # Research and evaluation use only — not for commercial use
> These weights are a quantized derivative of [Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1)
> and are distributed under the **Qwen Research License Agreement** ([LICENSE](LICENSE)).
> The license permits use, reproduction and distribution **for non-commercial purposes only**, defined as
> **research or evaluation**. Any commercial use requires a separate license from the licensor
> (model-business@notice.qwencloud.com). By downloading or using these files you agree to the LICENSE.

# mflux 8bit quantization of Qwen-Image-2.1

An Osaurus 8bit [mflux](https://github.com/filipstrand/mflux) quantization of
[Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1) for Apple Silicon (17 GB, closest to the original; recommended).
This is not an official Qwen release and is not endorsed by the Qwen team.

One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images);
the vision encoder is included.

## Changes from the original (LICENSE §3(b))
- Transformer and text/vision encoder weights re-saved with mflux and quantized to MLX affine 8-bit,
  group size 64 (modulation, timestep embedding and output norm kept in bf16).
- VAE re-saved in fp32, unquantized.
- No fine-tuning or other change to the model.

## Generated images
The Qwen team has stated that "Outputs are not part of the licensed Materials. Users retain the rights to
images and other content they generate using the model." This does not grant commercial use of the model
itself; running the model remains limited to research and evaluation unless you hold a commercial license.

## Use in Osaurus
Download it from the Image models tab, then generate or edit from chat or the image panel.
Defaults: 40 steps, guidance 1.0, sizes in multiples of 32.

## Use with mflux
```bash
mflux-generate-qwen-2.1-edit --model OsaurusAI/Qwen-Image-2.1-mflux-8bit \
  --prompt "A red panda reading a book under a cherry tree, watercolor" --seed 42
mflux-generate-qwen-2.1-edit --model OsaurusAI/Qwen-Image-2.1-mflux-8bit \
  --image-paths photo.png --prompt "Make the jacket dark green. Keep the face and pose." --seed 42
```

## Attribution and license
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory
Technology Co., Ltd. All Rights Reserved. See [LICENSE](LICENSE) and [NOTICE](NOTICE).

"Qwen" is a trademark of its owner; it is used here only to describe the base model. No trademark license is
granted or implied (LICENSE §5(b)).

Quantization: Osaurus · mflux 0.20 · 8bit · eric@osaurus.ai