---
title: Qwen-Image-2.1-mflux-q4
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-mflux-q4"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-mflux-q4.md"
repository: mlx-community/Qwen-Image-2.1-mflux-q4
last_updated: 2026-09-26
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2.1
base_model_relation: finetune
parameters: 331.0M
tensor_type:
  - F32
library_name:
  - mlx
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 669
stars: 2
tags:
  - mlx
  - mflux
  - text-to-image
  - image-to-image
  - qwen-image
---

# Qwen-Image-2.1-mflux-q4

> Qwen-Image-2.1-mflux-q4 - mlx-community 在 ModelScope 开源的模型。Qwen-Image-2.1 mflux q4

mlx-community/Qwen-Image-2.1-mflux-q4 是 ModelScope 魔搭社区上的 331.0M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image-2.1 构建。

- **Repository**: mlx-community/Qwen-Image-2.1-mflux-q4
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 331.0M
- **Base model**: Qwen/Qwen-Image-2.1
- **Tags**: mlx, mflux, text-to-image, image-to-image, qwen-image
- **Downloads**: 669
- **Stars**: 2
- **Last updated**: 2026-09-26

Source: https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-mflux-q4

---

# Qwen-Image-2.1 mflux q4

Native MLX/mflux q4 conversion of `Qwen/Qwen-Image-2.1` for Apple silicon.
The transformer and Qwen3-VL text encoder are both stored in MLX affine 4-bit
format; the VAE uses the mflux Qwen Image 2.1 layout.

This checkpoint was converted from upstream revision
`790c92633540aa0cb11d9abf19eb46d861714758` with mflux 0.20.0 and MLX 0.32.2.
It is intended for the reviewed low-memory loader in Rapid-MLX. Stock mflux
0.20.0 skips text-encoder quantization and cannot load this pack without that
loader change.

Measured during feasibility testing on a Mac Studio:

- 512x512, 40 steps: 4.68 GiB peak MLX memory
- 1024x1024, 4 steps: 5.14 GiB peak MLX memory
- packaged size: approximately 8.9 GB

These measurements used prompt materialization, encoder/transformer eviction,
a zero MLX cache, and tiled VAE decoding. Physical 8 GB and 16 GB Mac release
qualification is still required.

The original model and this conversion are licensed under Apache-2.0. See
`LICENSE` and the [upstream model](https://huggingface.co/Qwen/Qwen-Image-2.1).