---
title: Qwen-Image-2.1-Turbo-mflux-4bit
canonical_url: "https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit"
md_url: "https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit.md"
repository: OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit
last_updated: 2026-10-10
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2.1-Turbo
base_model_relation: quantized
parameters: 1.5B
tensor_type:
  - F32
  - BF16
  - U32
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 185
stars: 0
tags:
  - text-to-image
  - image-to-image
  - image-editing
  - mflux
  - quantized
  - osaurus
  - turbo
  - non-commercial
  - research-only
---

# Qwen-Image-2.1-Turbo-mflux-4bit

> Qwen-Image-2.1-Turbo-mflux-4bit - 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-Turbo and are distributed under the Qwen Research License Agreement…

OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit 是 ModelScope 魔搭社区上的 1.5B 参数text-to-image-synthesis模型，采用 other 许可，基于 Qwen/Qwen-Image-2.1-Turbo 构建。

- **Repository**: OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 1.5B
- **Base model**: Qwen/Qwen-Image-2.1-Turbo
- **Tags**: text-to-image, image-to-image, image-editing, mflux, quantized, osaurus, turbo, non-commercial, research-only
- **Downloads**: 185
- **Stars**: 0
- **Last updated**: 2026-10-10

Source: https://www.modelscope.cn/models/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit

---

![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-Turbo](https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo)
> 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.

# Qwen-Image-2.1-Turbo — mflux 4-bit

An Osaurus 4-bit [mflux](https://github.com/filipstrand/mflux) quantization of
[Qwen/Qwen-Image-2.1-Turbo](https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo) for Apple Silicon (9.9 GB, smallest; more composition drift between seeds).
This is not an official Qwen release and is not endorsed by the Qwen team.

Turbo is the 8-step distilled checkpoint of Qwen-Image-2.1. One bundle does both **text-to-image** and
**reference editing** (up to 10 ordered reference images); the vision encoder is included.

| Variant | Size | Notes |
|---|---|---|
| [8-bit](https://huggingface.co/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-8bit) | 17 GB | closest to the original; recommended |
| [6-bit](https://huggingface.co/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-6bit) | 14 GB | balanced size and quality |
| [4-bit](https://huggingface.co/OsaurusAI/Qwen-Image-2.1-Turbo-mflux-4bit) | 9.9 GB | smallest; more composition drift between seeds |

## Use in Osaurus
Requires **Osaurus 0.25.21 or newer**. Older versions treat this bundle as Qwen-Image-2.1 and sample it on that
model's 40-step schedule, which gives degraded images.

Download it from the Image models tab, then generate or edit from chat or the image panel.
Defaults: 8 steps on the model's fixed sampling grid, guidance 1.0 (no CFG), sizes in multiples of 32.

## Sampling
The model samples on the fixed 8-node sigma grid stored in `model_index.json` (`sample_sigmas`), used unshifted
with a terminal 0 and first-order Euler steps; there is no negative-prompt pass. A runtime that ignores this grid
and applies Qwen-Image-2.1's shifted schedule produces degraded images. Stock mflux does not read the grid yet.

## Changes from the original (LICENSE §3(b))
- Transformer and text/vision encoder weights re-saved with mflux and quantized to MLX affine 4-bit,
  group size 64 (modulation, timestep embedding and output norm kept in bf16).
- VAE re-saved in fp32, unquantized.
- `model_index.json` keeps the original 8-step `sample_sigmas` grid; 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.

## 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 (QwenImage21Edit save path) · 4-bit · eric@osaurus.ai