---
title: Ming-Image-0.1-Design-Layer-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Ming-Image-0.1-Design-Layer-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Ming-Image-0.1-Design-Layer-8bit.md"
repository: mlx-community/Ming-Image-0.1-Design-Layer-8bit
last_updated: 2026-09-27
license: mit
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - inclusionAI/Ming-Image-0.1-Design-Layer
base_model_relation: finetune
parameters: 3.2B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 109
stars: 0
tags:
  - mlx
  - safetensors
  - apple-silicon
  - image-to-image
  - layer-decomposition
  - rgba
  - graphic-design
  - diffusion
  - 8-bit
  - ming-image
---

# Ming-Image-0.1-Design-Layer-8bit

> Ming-Image-0.1-Design-Layer-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Ming-Image-0.1-Design-Layer-8bit

mlx-community/Ming-Image-0.1-Design-Layer-8bit 是 ModelScope 魔搭社区上的 3.2B 参数image-to-image模型，采用 mit 许可，基于 inclusionAI/Ming-Image-0.1-Design-Layer 构建。

- **Repository**: mlx-community/Ming-Image-0.1-Design-Layer-8bit
- **License**: mit
- **Tasks**: image-to-image
- **Parameters**: 3.2B
- **Base model**: inclusionAI/Ming-Image-0.1-Design-Layer
- **Tags**: mlx, safetensors, apple-silicon, image-to-image, layer-decomposition, rgba, graphic-design, diffusion, 8-bit, ming-image
- **Downloads**: 109
- **Stars**: 0
- **Last updated**: 2026-09-27

Source: https://www.modelscope.cn/models/mlx-community/Ming-Image-0.1-Design-Layer-8bit

---

# mlx-community/Ming-Image-0.1-Design-Layer-8bit

Pre-quantized MLX tier of **[inclusionAI/Ming-Image-0.1-Design-Layer](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design-Layer)** (MIT) for Apple
Silicon, loaded by the Swift/MLX port [ming-image-swift](https://github.com/xocialize/ming-image-swift). **8-bit tier** of the layer-decomposition model. It matches bf16 on every job we gate, and its memory fits a 48 GB Mac.

A Mac never has to hold the bf16 weights to use this tier. Total size: 28.3 GB; the bf16 repo is 49.8 GB. It is
part of the [Ming-Image (MLX) collection](https://huggingface.co/collections/mlx-community/ming-image-mlx-6ab8008988cbe1b217f90c61), next to
[mlx-community/Ming-Image-0.1-Design-Layer-bf16](https://huggingface.co/mlx-community/Ming-Image-0.1-Design-Layer-bf16).

## What is quantized

| Component | This tier |
|---|---|
| `mllm/`: MoE MLLM (attention, dense and shared-expert MLPs, the 256 routed experts) | 8-bit |
| `connector/`: Qwen2-1.5B connector | 8-bit |
| `transformer/`: DiT attention and feed-forward | 8-bit |
| Kept at full precision: the MoE routers, embeddings, norms, the Qwen2.5 ViT, the f32 projection heads (`mlp/`), the VAE, and the DiT's conditioning layers (adaLN, embedders, final layer) | bf16 / f32 |

Weight-only affine quantization, group size 64. The DiT never goes below 8 bits: weight-only int4 on a DiT is
real quality damage that buys no speed.

The layout is the [bf16 repo's](https://huggingface.co/mlx-community/Ming-Image-0.1-Design-Layer-bf16) upstream tree, with MLX
`.scales` / `.biases` stored beside each quantized weight and a `quantization` block in each quantized component's
`config.json`. The Swift loader reads it as published. Loading this repo gives parameters bit-identical to
quantizing the bf16 snapshot at load time (verified for every parameter).

## Quality

| Gate: five real signage stills at 512, plus one at 1024 (same noise as bf16) | bf16 | **8-bit** |
|---|---|---|
| Layers recomposited vs the input | 24.4–33.7 dB | **within 0.1 dB of bf16 on every job** |
| Layer coverage | — | identical |
| Stray text outside the text layer (the hardest still) | 26 chars | 30 chars |

Layer decomposition is driven mostly by the input image, so it is robust to quantizing the conditioning.

Full tables are in GATE-RESULTS §8 in the port's oracle (https://github.com/xocialize/ming-image-swift).

## Memory and speed

Measured on an M5 Max as process `phys_footprint`, with MLX's buffer cache capped at 2 GB (MLXEngine's default).

- Post-load resident: 7.6 GB. Peak process footprint: 28.1–28.4 GB for 4 to 12 layers at the 1024 bucket.
  The peak is the conditioning stage.
- MLXEngine declares 7.9 GB resident plus 25.1 GB activation, which is admitted on a 48 GB Mac. Requests are
  capped at 12 layers, the measured envelope.
- Speed (M5 Max, 12 steps, CFG 2.0): 137 s for 4 layers at the 512 bucket. bf16 takes 131 s.

## Use (Swift / MLXEngine)

```swift
import MLXMingImage
import MLXToolKit

let package = MingImageLayerPackage(configuration: MingImageLayerConfiguration(quant: .int8))
try await package.load()
let response = try await package.run(LayerDecomposeRequest(
    image: Image(format: .png, data: try Data(contentsOf: designURL)), spec: spec, resolution: 1024)) as! LayerDecomposeResponse
// response.layers[0] is the front-most layer; response.composite is the model's recomposition
```

Code: https://github.com/xocialize/ming-image-swift

## License

MIT, as the upstream weights. The upstream LICENSE is included.