---
license: apache-2.0
tags:
- mlx
- qwen
- image-generation
- text-to-image
- apple-silicon
- diffusion
base_model: Qwen/Qwen-Image-2512
library_name: mflux
---

# Qwen-Image-2512-8bit-MLX

MLX-optimized 8-bit quantized version of [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) for Apple Silicon.

First MLX port of Qwen-Image-2512.

## Quick Start

```bash
pip install mflux

mflux-generate-qwen \
  --model machiabeli/Qwen-Image-2512-8bit-MLX \
  --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-2512 (Dec 31, 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

## 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)