macOS
Homebrewverified · 100%
brew install ncnnlocal Homebrew formula metadata
brew / rank 3251
Install ncnn with Homebrew, dnf, Nix, pacman, zypper
High-performance neural network inference framework. Version 20260526 via Homebrew; verified 2026-06-25. Also installable with nix: nix profile install nixpkgs#ncnn.
install
Additional install commands
Linux
Fedora dnfverified · 92%
sudo dnf install ncnnFedora Rawhide package metadata · ncnn · source: dl.fedoraproject.org
Nixverified · 92%
nix profile install nixpkgs#ncnnnixpkgs package indexes · pkgs/by-name/nc/ncnn/package.nix · source: api.github.com
Arch Linux pacmanverified · 92%
sudo pacman -S ncnnArch Linux sync databases · ncnn · source: geo.mirror.pkgbuild.com
openSUSE zypperverified · 92%
sudo zypper install ncnnopenSUSE Tumbleweed package metadata · ncnn · source: download.opensuse.org
overview
Package summary
High-performance neural network inference framework
Project links
Commands and aliases
- caffe2ncnn
- darknet2ncnn
- mxnet2ncnn
- ncnn2int8
- ncnn2mem
- ncnn2table
- ncnnmerge
- ncnnoptimize
history
Project history and usage
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.
Project history
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.
Adoption history
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.
How it is used
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.
Why package nerds care
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.
Timeline
- 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
Sources
security posture
Risk level: blue
broad file, network, media, or database tool signal.
Risk classifier
blue risk · medium confidence · tool
Why
- broad file, network, media, or database tool signal
Signals
- text:network
Install behavior
- No Homebrew bottle metadata was recorded.
Recommended review
Before unattended agent use, check whether the tool reads plaintext credentials, writes remote state, publishes artifacts, or shells out to plugins.
executables
Installed executables
| Command | Kind | Exposure | Note |
|---|---|---|---|
caffe2ncnn | executable | indexed executable | Discovered from the local executable index. |
darknet2ncnn | executable | indexed executable | Discovered from the local executable index. |
mxnet2ncnn | executable | indexed executable | Discovered from the local executable index. |
ncnn2int8 | executable | indexed executable | Discovered from the local executable index. |
ncnn2mem | executable | indexed executable | Discovered from the local executable index. |
ncnn2table | executable | indexed executable | Discovered from the local executable index. |
ncnnmerge | executable | indexed executable | Discovered from the local executable index. |
ncnnoptimize | executable | indexed executable | Discovered from the local executable index. |
freshness
Version and freshness
These signals separate page generation age, package-manager activity, and upstream release comparison. Version lag is warned only when an evidence URL and comparable versions are present.
page generated2026-08-03
manager version20260526
manager updated2026-06-25
local dataunknown
upstreamnot available
latest detectednot detected
- okNo freshness warnings were generated.
install metadata
Package metadata
| Package key | brew:ncnn |
|---|---|
| Version | 20260526 |
| Package manager | Homebrew |
| Homepage | https://github.com/Tencent/ncnn |
| Repository | https://github.com/Tencent/ncnn |
| Last updated | 2026-06-25T13:37:56+02:00 |
| Pulse | updated |
| Bottle | not recorded |
| Service | none declared |
source database matches
Other package-manager records
Matches are pulled from external package-manager indexes and kept separate from local Automic Vault package links.
Nix95%
ncnn
nix profile install nixpkgs#ncnn- normalized package name match
- Matched by: Ncnn
dnf95%
ncnn 20250916-5.fc45
A high-performance neural network inference framework
https://github.com/Tencent/ncnn
sudo dnf install ncnn- License: BSD-3-Clause AND BSD-2-Clause AND Zlib
- Category: Unspecified
- Architecture: i686
- Source Package: ncnn
- 9 dependencies
- 2 provides
- normalized package name match
- Matched by: Ncnn
dnf95%
ncnn-devel 20250916-5.fc45
Development files for ncnn
https://github.com/Tencent/ncnn
sudo dnf install ncnn-devel- License: BSD-3-Clause AND BSD-2-Clause AND Zlib
- Category: Unspecified
- Architecture: i686
- Source Package: ncnn
- 13 dependencies
- 3 provides
- normalized package name match
- Matched by: Ncnn
pacman95%
ncnn 20260526-6
High-performance neural network inference framework optimized for the mobile platform
https://github.com/Tencent/ncnn
sudo pacman -S ncnn- License: BSD-3-Clause
- Architecture: x86_64
- 6 dependencies
- 1 optional deps
- normalized package name match
- Matched by: Ncnn
zypper95%
libncnn1 20250916-1.10
NCNN library
https://github.com/Tencent/ncnn
sudo zypper install libncnn1- License: BSD-2-Clause AND BSD-3-Clause AND Zlib
- Category: System/Libraries
- Architecture: x86_64
- Source Package: ncnn
- 7 dependencies
- 2 provides
- normalized package name match
- Matched by: Ncnn
zypper95%
ncnn 20250916-1.10
A high-performance neural network inference framework
https://github.com/Tencent/ncnn
sudo zypper install ncnn- License: BSD-2-Clause AND BSD-3-Clause AND Zlib
- Category: Development/Tools/Other
- Architecture: x86_64
- Source Package: ncnn
- 7 dependencies
- 1 provides
- normalized package name match
- Matched by: Ncnn
zypper95%
ncnn-devel 20250916-1.10
Development tools for ncnn
https://github.com/Tencent/ncnn
sudo zypper install ncnn-devel- License: BSD-2-Clause AND BSD-3-Clause AND Zlib
- Category: Development/Libraries/C and C++
- Architecture: x86_64
- Source Package: ncnn
- 2 dependencies
- 3 provides
- normalized package name match
- Matched by: Ncnn
source trail
Generated from repository data
This page is generated by av-web from the private package SQLite artifact built by scripts/generate-pkg-sqlite.py.
Combined YAML source
View the package source record on GitHub.
Used sources
- Geiger risk classifier
- cross-ecosystem install command graph
- curated package history
- external package-manager database matches
- pkg.so package database
- pkgdb category and tag curation