---
title: Qwen-Image-2512-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2512-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen-Image-2512-8bit.md"
repository: mlx-community/Qwen-Image-2512-8bit
last_updated: 2026-01-01
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image
base_model_relation: finetune
parameters: 10.0B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - mlx
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1355
stars: 3
tags:
  - mlx
  - qwen
  - image-generation
  - text-to-image
  - apple-silicon
  - diffusion
---

# Qwen-Image-2512-8bit

> Qwen-Image-2512-8bit - mlx-community 在 ModelScope 开源的模型。Qwen-Image 8-bit MLX

mlx-community/Qwen-Image-2512-8bit 是 ModelScope 魔搭社区上的 10.0B 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image 构建。

- **Repository**: mlx-community/Qwen-Image-2512-8bit
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 10.0B
- **Base model**: Qwen/Qwen-Image
- **Tags**: mlx, qwen, image-generation, text-to-image, apple-silicon, diffusion
- **Downloads**: 1355
- **Stars**: 3
- **Last updated**: 2026-01-01

Source: https://www.modelscope.cn/models/mlx-community/Qwen-Image-2512-8bit

---

# Qwen-Image 8-bit MLX

MLX-optimized 8-bit quantized version of [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) for Apple Silicon.

**First MLX port of Qwen-Image!** 🎉

## Quick Start

```bash
pip install mflux

mflux-generate-qwen \
  --model mlx-community/Qwen-Image-2512-8bit \
  --prompt "A photorealistic cat wearing a tiny top hat" \
  --steps 20
```

## Performance

| Metric | Value |
|--------|-------|
| Size | 34GB (8-bit quantized) |
| Speed | ~8.5s/step on M-series Mac |
| 20 steps | ~2:50 total |

## Model Details

- **Base Model:** Qwen/Qwen-Image (Dec 2025)
- **Quantization:** 8-bit
- **Framework:** MLX (Apple Silicon optimized)
- **Converted with:** mflux 0.14.0

## Hardware Requirements

- Apple Silicon Mac (M1/M2/M3/M4/M5)
- ~40GB unified memory recommended for 8-bit

## Sample Output

Generated with prompt: "A photorealistic cat wearing a tiny top hat, studio lighting"

## All Quantizations

- [8-bit](https://huggingface.co/mlx-community/Qwen-Image-2512-8bit) (34GB)
- [6-bit](https://huggingface.co/mlx-community/Qwen-Image-2512-6bit) (29GB)
- [5-bit](https://huggingface.co/mlx-community/Qwen-Image-2512-5bit) (27GB)
- [4-bit](https://huggingface.co/mlx-community/Qwen-Image-2512-4bit) (24GB)
- [3-bit](https://huggingface.co/mlx-community/Qwen-Image-2512-3bit) (22GB)

## License

Apache 2.0 (same as base model)

## Credits

- Original model: [Qwen Team](https://huggingface.co/Qwen)
- MLX framework: [Apple ML Explore](https://github.com/ml-explore/mlx)
- mflux: [filipstrand](https://github.com/filipstrand/mflux)