# 使用 Homebrew, dnf, Nix, pacman, zypper 安装 ncnn

查看 ncnn 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。

## 安装

```sh
sudo av install brew:ncnn
```

其他安装命令:

### macOS

- Homebrew (100%):

```sh
brew install ncnn
```

  证据: local Homebrew formula metadata

### Linux

- dnf (92%):

```sh
sudo dnf install ncnn
```

  证据: Fedora Rawhide package metadata: ncnn from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst

- Nix (92%):

```sh
nix profile install nixpkgs#ncnn
```

  证据: nixpkgs package indexes: pkgs/by-name/nc/ncnn/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1

- pacman (92%):

```sh
sudo pacman -S ncnn
```

  证据: Arch Linux sync databases: ncnn from https://geo.mirror.pkgbuild.com/extra/os/x86_64/extra.db.tar.gz

- zypper (92%):

```sh
sudo zypper install ncnn
```

  证据: openSUSE Tumbleweed package metadata: ncnn from https://download.opensuse.org/tumbleweed/repo/oss/repodata/50b07339cb64c8ed4091bdbabddadc1ff5737b090e478818a195b40d8a3292861a879139b4a3987c31109699fde9fbf4a716367ddf4eef77da75f96e3193d6ed-primary.xml.zst

## 软件包事实

- **软件包键:** brew:ncnn
- **软件包管理器:** Homebrew
- **软件包管理器页面:** <https://formulae.brew.sh/formula/ncnn>
- **版本:** 20260526
- **来源摘要:** High-performance neural network inference framework
- **主页:** <https://github.com/Tencent/ncnn>
- **仓库:** <https://github.com/Tencent/ncnn>
- **许可证:** BSD-3-Clause
- **源码归档:** <https://github.com/Tencent/ncnn/archive/refs/tags/20260526.tar.gz>
- **最后更新:** 2026-06-25T13:37:56+02:00
- **已生成:** 2026-08-04T22:13:35+00:00

## 可执行文件

- caffe2ncnn (cli)
- darknet2ncnn (cli)
- mxnet2ncnn (cli)
- ncnn2int8 (cli)
- ncnn2mem (cli)
- ncnn2table (cli)
- ncnnmerge (cli)
- ncnnoptimize (cli)
- caffe2ncnn (别名)
- darknet2ncnn (别名)
- mxnet2ncnn (别名)
- ncnn2int8 (别名)
- ncnn2mem (别名)
- ncnn2table (别名)
- ncnnmerge (别名)
- ncnnoptimize (别名)

## 依赖

- abseil
- glslang
- libomp
- molten-vk
- protobuf
- spirv-tools

## 构建依赖

- cmake

## 安装行为

- post-install 钩子: 未定义
- Bottle: 可用 于 arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux

## 版本和新鲜度

- 页面生成时间: 2026-08-04
- 管理器版本: 20260526
- 管理器更新时间: 2026-06-25
- 本地数据: OK
- 上游仓库: https://github.com/Tencent/ncnn
- 信息: No cached GitHub release or tag data was available.
## 项目历史与用法

ncnn is Tencent's open-source neural-network inference runtime for mobile, embedded, desktop, browser, and edge deployment. Its niche is small, dependency-light inference: the upstream README emphasizes no third-party runtime dependencies, CPU and Vulkan GPU backends, explicit low-memory allocator design, and conversion tools such as pnnx for PyTorch and ONNX workflows.

### 项目历史

Tencent presentations describe the ncnn project as dating from 2017, with open collaboration and Vulkan acceleration as central design points. That timing put it in the wave of mobile inference runtimes that appeared after deep-learning deployment moved from server GPUs into phones and edge devices.

### 采用历史

Upstream states that ncnn is used in Tencent applications including QQ, Qzone, WeChat, and Pitu. Outside Tencent, its adoption pattern is typical for low-level ML infrastructure: package-manager availability, examples for object detection and vision models, and use by developers who want a C++ runtime without TensorFlow Lite or ONNX Runtime-sized baggage.

### 使用方式

Package users usually install ncnn for the converter and optimizer executables as much as for the library. A common flow is export from PyTorch through pnnx, produce .param and .bin model files, run optimization or int8 tooling, and embed the resulting model in a C++ or mobile application using ncnn::Net.

### 为什么软件包爱好者会关心

For package maintainers, ncnn is interesting because it is a fast-moving C++/Vulkan project that exposes both libraries and many small CLI tools. It is also a useful example of a Homebrew formula where the command-line surface is mostly build/deployment tooling around a library rather than one end-user command.

### 时间线

- 2017: Tencent presentation material describes ncnn as active since 2017.
- 2020s: README documents pnnx-based PyTorch/ONNX conversion and CPU/Vulkan deployment across mobile, desktop, browser, and edge targets.

### Related projects

- PyTorch, ONNX, pnnx, Vulkan, TensorFlow, Caffe, MXNet, Darknet

### 来源

- <https://formulae.brew.sh/formula/ncnn>
- <https://github.com/Tencent/ncnn>
- <https://www.khronos.org/developers/linkto/ncnn-universal-neural-network-inference-with-vulkan>


## 安全说明

broad file, network, media, or database tool signal.

- **Geiger 风险:** blue / 中
- broad file, network, media, or database tool signal

## 源数据库详情

- **Source Database:** Homebrew formula API
- **Tap:** homebrew/core
- **Full Name:** ncnn
- **Version Scheme:** 0
- **Revision:** 1
- **Head Version:** HEAD
- **Bottle Stable Root URL:** <https://ghcr.io/v2/homebrew/core>
- **Deprecated:** no
- **Disabled:** no
- **Keg Only:** no
- **URL Keys:** head, stable

## 其他软件包管理器记录

- Nix - ncnn: normalized package name match | nixpkgs package indexes: pkgs/by-name/nc/ncnn/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1
- dnf - ncnn - 20250916-5.fc45: normalized package name match | Fedora Rawhide package metadata: ncnn from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst | A high-performance neural network inference framework | https://github.com/Tencent/ncnn
- dnf - ncnn-devel - 20250916-5.fc45: normalized package name match | Fedora Rawhide package metadata: ncnn-devel from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst | Development files for ncnn | https://github.com/Tencent/ncnn
- pacman - ncnn - 20260526-6: normalized package name match | Arch Linux sync databases: ncnn from https://geo.mirror.pkgbuild.com/extra/os/x86_64/extra.db.tar.gz | High-performance neural network inference framework optimized for the mobile platform | https://github.com/Tencent/ncnn
- zypper - libncnn1 - 20250916-1.10: normalized package name match | openSUSE Tumbleweed package metadata: libncnn1 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/50b07339cb64c8ed4091bdbabddadc1ff5737b090e478818a195b40d8a3292861a879139b4a3987c31109699fde9fbf4a716367ddf4eef77da75f96e3193d6ed-primary.xml.zst | NCNN library | https://github.com/Tencent/ncnn
- zypper - ncnn - 20250916-1.10: normalized package name match | openSUSE Tumbleweed package metadata: ncnn from https://download.opensuse.org/tumbleweed/repo/oss/repodata/50b07339cb64c8ed4091bdbabddadc1ff5737b090e478818a195b40d8a3292861a879139b4a3987c31109699fde9fbf4a716367ddf4eef77da75f96e3193d6ed-primary.xml.zst | A high-performance neural network inference framework | https://github.com/Tencent/ncnn
- zypper - ncnn-devel - 20250916-1.10: normalized package name match | openSUSE Tumbleweed package metadata: ncnn-devel from https://download.opensuse.org/tumbleweed/repo/oss/repodata/50b07339cb64c8ed4091bdbabddadc1ff5737b090e478818a195b40d8a3292861a879139b4a3987c31109699fde9fbf4a716367ddf4eef77da75f96e3193d6ed-primary.xml.zst | Development tools for ncnn | https://github.com/Tencent/ncnn


## 相关链接

- [Source-control packages](https://pkg.so/zh-hans/source-control-tools/) - Belongs to a source-control command family.
- [MCP tool packages](https://pkg.so/zh-hans/mcp-tools/) - Mentions MCP or Model Context Protocol.
- [Secret-risk packages](https://pkg.so/zh-hans/secret-risk-packages/) - Has protected-tool coverage, approval-gate, or non-low Geiger security signals.
- [AI and agent packages](https://pkg.so/zh-hans/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata.
- [protobuf](https://pkg.so/zh-hans/brew/protobuf/) - Runtime dependency declared by Homebrew.
- [spirv-tools](https://pkg.so/zh-hans/brew/spirv-tools/) - Runtime dependency declared by Homebrew.
- [molten-vk](https://pkg.so/zh-hans/brew/molten-vk/) - Runtime dependency declared by Homebrew.
- [glslang](https://pkg.so/zh-hans/brew/glslang/) - Runtime dependency declared by Homebrew.
- [cmake](https://pkg.so/zh-hans/brew/cmake/) - Build dependency declared by Homebrew.
- [opencv](https://pkg.so/zh-hans/brew/opencv/) - Shares pkgdb curated category or tags: ai, cli, computer-vision, machine-learning, ml-tools.
- [text-embeddings-inference](https://pkg.so/zh-hans/brew/text-embeddings-inference/) - Shares pkgdb curated category or tags: ai, cli, inference, machine-learning, ml-tools.
- [djl-serving](https://pkg.so/zh-hans/brew/djl-serving/) - Shares pkgdb curated category or tags: ai, cli, inference, machine-learning, ml-tools.
- [tesseract](https://pkg.so/zh-hans/brew/tesseract/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools.
- [openvino](https://pkg.so/zh-hans/brew/openvino/) - Shares pkgdb curated category or tags: ai, cli, computer-vision, ml-tools.
- [pytorch](https://pkg.so/zh-hans/brew/pytorch/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools.
- [mlx](https://pkg.so/zh-hans/brew/mlx/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools.
- [hf](https://pkg.so/zh-hans/brew/hf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools.
- [mlx-lm](https://pkg.so/zh-hans/brew/mlx-lm/) - Local package facts share a topical domain. Shared terms: ai, cli, inference, learning, machine.

## Combined YAML source

View the package source record on GitHub. [combined/ncnn.yml](https://github.com/mxcl/pkgdb/blob/main/combined/ncnn.yml)


## 来源

- pkg.so package database
- Geiger risk classifier
- package-page enrichment
- curated package history
- package version freshness
- pkgdb category and tag curation
- package relationship graph
- external package-manager database matches
- cross-ecosystem install command graph