Modelpublic

machiabeli/Qwen-Image-2512-4bit-MLX

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face

0likes1.9kdownloads

Model Card

Qwen-Image-2512-4bit-MLX

MLX-optimized 4-bit quantized version of Qwen-Image-2512 for Apple Silicon.

Quick Start

bash

pip install mflux

mflux-generate-qwen \
  --model machiabeli/Qwen-Image-2512-4bit-MLX \
  --prompt "A photorealistic cat wearing a tiny top hat" \
  --steps 20

Model Details

—Base Model: Qwen/Qwen-Image-2512 (Dec 31, 2025)
—Quantization: 4-bit
—Framework: MLX (Apple Silicon optimized)
—Converted with: mflux 0.14.0

Other Quantizations

—8-bit (34GB)
—6-bit (29GB)
—4-bit (24GB)

License

Apache 2.0 (same as base model)