---
title: u2net-mlx
canonical_url: "https://www.modelscope.cn/models/theMindStudio/u2net-mlx"
md_url: "https://www.modelscope.cn/models/theMindStudio/u2net-mlx.md"
repository: theMindStudio/u2net-mlx
last_updated: 2026-01-12
license: apache-2.0
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
parameters: 44.0M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
downloads: 213
stars: 0
tags:
  - mlx
  - u2-net
  - background-removal
  - image-segmentation
  - apple-silicon
---

# u2net-mlx

> u2net-mlx - theMindStudio 在 ModelScope 开源的模型。U2-Net (MLX Format) This is a converted version of U-2-Net for macOS, optimized for Apple Silicon using the MLX framework. It enables efficient background removal on macOS GPU/ANE without heavy PyTorch dependencies.

theMindStudio/u2net-mlx 是 ModelScope 魔搭社区上的 44.0M 参数image-segmentation模型，采用 apache-2.0 许可。

- **Repository**: theMindStudio/u2net-mlx
- **License**: apache-2.0
- **Tasks**: image-segmentation
- **Parameters**: 44.0M
- **Tags**: mlx, u2-net, background-removal, image-segmentation, apple-silicon
- **Downloads**: 213
- **Stars**: 0
- **Last updated**: 2026-01-12

Source: https://www.modelscope.cn/models/theMindStudio/u2net-mlx

---

# U2-Net (MLX Format)
This is a converted version of [U-2-Net](https://github.com/xuebinqin/U-2-Net) for macOS, optimized for Apple Silicon using the [MLX framework](https://github.com/ml-explore/mlx).
It enables efficient background removal on macOS GPU/ANE without heavy PyTorch dependencies.