---
title: Boogu-Image-0.1-Base-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Base-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Base-4bit.md"
repository: mlx-community/Boogu-Image-0.1-Base-4bit
last_updated: 2026-06-21
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Boogu/Boogu-Image-0.1-Base
base_model_relation: finetune
parameters: 2.9B
tensor_type:
  - F32
  - U32
  - BF16
library_name:
  - mlx
  - lora
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 29
stars: 1
tags:
  - mlx
  - safetensors
  - apple-silicon
  - text-to-image
  - image-editing
  - diffusion
  - omnigen2
  - boogu
---

# Boogu-Image-0.1-Base-4bit

> Boogu-Image-0.1-Base-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Boogu-Image-0.1-Base-4bit

mlx-community/Boogu-Image-0.1-Base-4bit 是 ModelScope 魔搭社区上的 2.9B 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Boogu/Boogu-Image-0.1-Base 构建。

- **Repository**: mlx-community/Boogu-Image-0.1-Base-4bit
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.9B
- **Base model**: Boogu/Boogu-Image-0.1-Base
- **Tags**: mlx, safetensors, apple-silicon, text-to-image, image-editing, diffusion, omnigen2, boogu
- **Downloads**: 29
- **Stars**: 1
- **Last updated**: 2026-06-21

Source: https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Base-4bit

---

# 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`](https://huggingface.co/collections/mlx-community/qwen3-vl), not re-hosted.

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