---
title: Qwen-Image-2.1-MLX-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-MLX-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-MLX-4bit.md"
repository: mlx-community/Qwen-Image-2.1-MLX-4bit
last_updated: 2026-09-21
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2.1
base_model_relation: finetune
parameters: 2.9B
tensor_type:
  - F32
  - BF16
  - U32
library_name:
  - mlx
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1638
stars: 0
tags:
  - mlx
  - qwen-image
  - text-to-image
---

# Qwen-Image-2.1-MLX-4bit

> Qwen-Image-2.1-MLX-4bit - mlx-community 在 ModelScope 开源的模型。Qwen-Image-2.1 (MLX, 4-bit)

mlx-community/Qwen-Image-2.1-MLX-4bit 是 ModelScope 魔搭社区上的 2.9B 参数text-to-image-synthesis模型，采用 other 许可，基于 Qwen/Qwen-Image-2.1 构建。

- **Repository**: mlx-community/Qwen-Image-2.1-MLX-4bit
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.9B
- **Base model**: Qwen/Qwen-Image-2.1
- **Tags**: mlx, qwen-image, text-to-image
- **Downloads**: 1638
- **Stars**: 0
- **Last updated**: 2026-09-21

Source: https://www.modelscope.cn/models/mlx-community/Qwen-Image-2.1-MLX-4bit

---

# Qwen-Image-2.1 (MLX, 4-bit)

MLX conversion of [Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1),
a single-stream DiT text-to-image + image-editing model with a Qwen3-VL text
encoder and a 64-channel RGBA VAE. Governed by the Qwen Research License.