Modelpublic

mlx-community/Boogu-Image-0.1-Base-4bit

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

6likes

Model Card

mlx-community/Boogu-Image-0.1-Base-4bit

MLX (int4) conversion of [Boogu-Image-0.1-Base](https://huggingface.co/Boogu/Boogu-Image-0.1-Base) (Apache-2.0) for Apple Silicon — bilingual (EN/ZH) text-to-image. OmniGen2-lineage pipeline (DiT + FLUX.1 VAE + FlowMatchEuler scheduler). The Qwen3-VL-8B-Instruct text encoder is the stock model (verified bit-identical) — referenced from `mlx-community/Qwen3-VL-8B-Instruct`, not re-hosted.

Quantization: attn+FFN Linears int4 (groupsize=32); per-pass cosine vs bf16 **0.99896**. ~7.4 GB. Quant auto-detected via `transformer/quantconfig.json`.

Parity (CPU stream, fp32)

—FLUX VAE decode: max_abs 6.7e-6 · encode 1.97e-4
—Scheduler (flow-match + time-shift): bit-exact
—Full DiT (40-layer): max_abs 1.56e-5

Use

bash

pip install mlx mlx-vlm
git clone https://github.com/xocialize/boogu-image-mlx && cd boogu-image-mlx && pip install -e .

python

from boogu_image_mlx.pipeline_mlx import BooguImagePipeline
from PIL import Image
pipe = BooguImagePipeline.from_pretrained("<this repo dir>", "mlx-community/Qwen3-VL-8B-Instruct")
img = pipe.generate("a red panda surfing on a wave, photorealistic", height=1024, width=1024, steps=30, guidance=3.5)
Image.fromarray(img).save("out.png")

Code: https://github.com/xocialize/boogu-image-mlx