pkg.soopen package index

brew / Rang 206

llama.cpp mit Homebrew, dnf, Nix, pacman, apk, MacPorts, winget installieren

Prüfe Installationswege, Executables, Metadaten und Sicherheitshinweise für llama.cpp in AI-Agent-Workflows.

InstallationsbefehlSicherheitshinweise

Installation

Weitere Installationsbefehle

macOS

Homebrewverifiziert · 100%
brew install llama.cpp

local Homebrew formula metadata

MacPortsverifiziert · 94%
sudo port install llama.cpp

MacPorts ports tree · llm/llama.cpp/Portfile · Quelle: api.github.com

Linux

Fedora dnfverifiziert · 92%
sudo dnf install llama-cpp

Fedora Rawhide package metadata · llama-cpp · Quelle: dl.fedoraproject.org

Nixverifiziert · 92%
nix profile install nixpkgs#llama-cpp

nixpkgs package indexes · pkgs/by-name/ll/llama-cpp/package.nix · Quelle: api.github.com

Arch Linux pacmanverifiziert · 92%
sudo pacman -S llama-cpp

Arch Linux sync databases · llama-cpp · Quelle: geo.mirror.pkgbuild.com

Alpine Linux apkverifiziert · 92%
sudo apk add llama-batched

Alpine Linux edge package indexes · llama-batched · Quelle: dl-cdn.alpinelinux.org

Windows

Windows Package Managerverifiziert · 92%
winget install --id ggml.llamacpp -e

Windows Package Manager source index · ggml.llamacpp · Quelle: cdn.winget.microsoft.com

Überblick

Paketzusammenfassung

LLM inference in C/C++

Befehle und Aliase

  • llama
  • llama-batched
  • llama-batched-bench
  • llama-bench
  • llama-cli
  • llama-completion
  • llama-debug
  • llama-diffusion-cli
  • llama-embedding
  • llama-eval-callback
  • llama-finetune
  • llama-fit-params
  • llama-gen-docs
  • llama-gguf
  • llama-gguf-hash
  • llama-gguf-split
  • llama-idle
  • llama-imatrix
  • llama-lookahead
  • llama-lookup
  • llama-lookup-create
  • llama-lookup-merge
  • llama-lookup-stats
  • llama-mtmd-cli
  • llama-parallel
  • llama-passkey
  • llama-perplexity
  • llama-quantize
  • llama-results
  • llama-retrieval
  • llama-server
  • llama-simple

Verlauf

Projektgeschichte und Nutzung

llama.cpp is one of the defining packages of the local-LLM era: a C/C++ inference stack that made it practical to run quantized transformer models on laptops, desktops, servers, and small devices without a heavyweight Python runtime.

Projektgeschichte

The repository was created on GitHub on March 10, 2023, shortly after Meta's LLaMA model release changed the center of gravity for local language-model experimentation. The README states the project goal as LLM inference with minimal setup and strong performance across local and cloud hardware.

The project is closely tied to ggml. Its README describes llama.cpp as the main playground for developing new ggml features, and the implementation grew around plain C/C++, integer quantization, CPU backends, and hardware accelerators such as Metal, CUDA, Vulkan, SYCL, HIP, and related GPU paths.

As model support broadened beyond the original LLaMA family, llama.cpp became a runtime and tooling umbrella: converters, quantizers, benchmarking tools, embedding tools, an OpenAI-compatible server, multimodal support, and many model-family loaders are represented in the command set and documentation.

Adoptionsgeschichte

Package adoption spread because llama.cpp lowered the cost of trying local inference: build from source, install from Homebrew, Nix, winget, conda-forge, Docker, or download release binaries, then run a model file or fetch one from Hugging Face-oriented workflows.

The README's bindings list shows the surrounding ecosystem that formed around the C/C++ core, including Python, Go, Node.js, Ruby, browser/Wasm, editor-completion plugins, and server clients. That ecosystem made llama.cpp both an end-user CLI and a library/runtime target for other packages.

Its high-frequency build-tag release pattern reflects active downstream pressure: package managers, bindings, model hubs, and local-AI applications all depend on fast propagation of backend, quantization, and model-format changes.

Wie es verwendet wird

Users run llama-cli for local prompts, llama-server for an OpenAI-compatible HTTP API, llama-bench for performance testing, llama-quantize for smaller model files, and many auxiliary tools for embeddings, perplexity, retrieval, tokenization, and model-file manipulation.

The package is especially useful when a developer wants a self-contained inference engine: compile once, point it at a model, and choose a CPU/GPU backend without adopting a full ML framework stack.

Warum Paket-Nerds sich dafür interessieren

For package maintainers, llama.cpp is unusually dynamic: hardware backend flags, model-format transitions, CLI renames, bundled tools, and release cadence all matter. It turned local AI into something package managers had to treat like a fast-moving systems tool rather than a single Python application.

It is also a packaging bridge between model hubs and Unix tooling. The same project can be installed as a formula, used as a server daemon, linked by language bindings, wrapped by desktop apps, or embedded in another inference product.

Zeitleiste

  • 2023: ggml-org/llama.cpp repository created on March 10.
  • 2023: The project manifesto discussion documented goals and direction for the early community.
  • 2024: llama.cpp issue trackers began maintaining separate API changelogs for libllama and llama-server.
  • 2025: Multimodal support reached llama-server through the upstream pull request and documentation referenced from the README.
  • 2026: Homebrew, Nix, winget, conda-forge, Docker, and release binaries were documented installation paths in the upstream README.

Related projects

  • ggml is the closest related project, because llama.cpp is the main development playground for that tensor library.
  • Important downstream and adjacent projects include llama-cpp-python, node-llama-cpp, go-llama.cpp, wllama, llama.vscode, llama.vim, and applications that wrap llama-server's OpenAI-compatible API.

Sicherheitslage

Noch keine Protected-Tool-Abdeckung gefunden

Für llama.cpp wurde kein passendes lokales Secret-Handling-Manifest gefunden. Paketmetadaten bleiben hier veröffentlicht, damit künftige Abdeckung eine stabile Paket-URL hat.

Installationsverhalten

  • In den Formelmetadaten ist kein Homebrew-Post-install-Hook erfasst.
  • Homebrew-Bottle-Metadaten sind für 6 Plattformziele verfügbar.
  • Installiert mit 2 Laufzeitabhängigkeiten.
  • Build-Metadaten listen 1 Build-Abhängigkeiten.

Empfohlene Prüfung

Prüfe vor unbeaufsichtigter Agent-Nutzung, ob das Tool Klartext-Credentials liest, Remote-Zustand schreibt, Artefakte veröffentlicht oder Plugins ausführt.

Executables

Installierte Executables

BefehlArtSichtbarkeitHinweis
llamacliglobales Executable
llama-batchedcliglobales Executable
llama-batched-benchcliglobales Executable
llama-benchcliglobales Executable
llama-clicliglobales Executable
llama-completioncliglobales Executable
llama-debugcliglobales Executable
llama-diffusion-clicliglobales Executable
llama-embeddingcliglobales Executable
llama-eval-callbackcliglobales Executable
llama-finetunecliglobales Executable
llama-fit-paramscliglobales Executable
llama-gen-docscliglobales Executable
llama-ggufcliglobales Executable
llama-gguf-hashcliglobales Executable
llama-gguf-splitcliglobales Executable
llama-idlecliglobales Executable
llama-imatrixcliglobales Executable
llama-lookaheadcliglobales Executable
llama-lookupcliglobales Executable
llama-lookup-createcliglobales Executable
llama-lookup-mergecliglobales Executable
llama-lookup-statscliglobales Executable
llama-mtmd-clicliglobales Executable
llama-parallelcliglobales Executable
llama-passkeycliglobales Executable
llama-perplexitycliglobales Executable
llama-quantizecliglobales Executable
llama-resultscliglobales Executable
llama-retrievalcliglobales Executable
llama-servercliglobales Executable
llama-simplecliglobales Executable
llama-simple-chatcliglobales Executable
llama-speculativecliglobales Executable
llama-speculative-simplecliglobales Executable
llama-tokenizecliglobales Executable
llama-ttscliglobales Executable

Aktualität

Version und Aktualität

Diese Signale trennen das Alter der Seitengenerierung, Aktivität des Paketmanagers und Upstream-Release-Vergleich. Versionsrückstand wird nur gemeldet, wenn eine Evidenz-URL und vergleichbare Versionen vorhanden sind.

Seite generiert2026-09-19
Manager-Version0.4.1
Manager aktualisiert2026-09-18
lokale DatenOK
Upstreamnot checked
neueste erkannte Versionnicht erkannt

https://github.com/ggml-org/llama.cpp

Installationsmetadaten

Paketmetadaten

Paketschlüsselbrew:llama.cpp
Version0.4.1
PaketmanagerHomebrew
Paketmanager-Seitehttps://formulae.brew.sh/formula/llama.cpp
Homepagehttps://llama.app
Repositoryhttps://github.com/ggml-org/llama.cpp
Upstream-Dokumentationhttps://llama.app
LizenzMIT
Quellarchivhttps://github.com/ggml-org/llama.cpp.git
Zuletzt aktualisiert2026-09-18T13:15:15+02:00
Pulseupdated
Abhängigkeitenggml, openssl@3
Build-Abhängigkeitencmake
Bottleverfügbar (auf arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux)
Homebrew post-installnicht definiert
Dienstkeiner deklariert

Registry-Fakten

Details aus der Quelldatenbank

Source DatabaseHomebrew formula API
Taphomebrew/core
Full Namellama.cpp
Version Scheme1
Revision0
Head VersionHEAD
Bottle Stable Root URLhttps://ghcr.io/v2/homebrew/core
Deprecatedno
Disabledno
Keg Onlyno
URL Keys
  • head
  • stable

Source-Datenbank-Treffer

Andere Paketmanager-Einträge

Treffer stammen aus externen Paketmanager-Indizes und bleiben von lokalen Automic-Vault-Paketlinks getrennt.

Nix95%

llama-cpp

nix profile install nixpkgs#llama-cpp
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
nixpkgs package indexes · api.github.com · nixpkgs package indexes: pkgs/by-name/ll/llama-cpp/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1
apk95%

llama-batched 0.2.0-r1

llama-batched tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-batched
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-batched from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-batched-bench 0.2.0-r1

llama-batched-bench tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-batched-bench
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-batched-bench from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-completion 0.2.0-r1

llama-completion tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-completion
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-completion from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-debug 0.2.0-r1

llama-debug tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-debug
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-debug from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-diffusion-cli 0.2.0-r1

llama-diffusion-cli tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-diffusion-cli
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-diffusion-cli from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-embedding 0.2.0-r1

llama-embedding tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-embedding
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-embedding from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-eval-callback 0.2.0-r1

llama-eval-callback tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-eval-callback
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-eval-callback from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-finetune 0.2.0-r1

llama-finetune tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-finetune
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-finetune from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-fit-params 0.2.0-r1

llama-fit-params tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-fit-params
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-fit-params from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-gen-docs 0.2.0-r1

llama-gen-docs tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-gen-docs
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-gen-docs from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-gguf 0.2.0-r1

llama-gguf tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-gguf
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-gguf from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-gguf-hash 0.2.0-r1

llama-gguf-hash tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-gguf-hash
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-gguf-hash from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-gguf-split 0.2.0-r1

llama-gguf-split tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-gguf-split
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-gguf-split from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-idle 0.2.0-r1

llama-idle tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-idle
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-idle from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz
apk95%

llama-imatrix 0.2.0-r1

llama-imatrix tool from llama.cpp

https://github.com/ggml-org/llama.cpp

sudo apk add llama-imatrix
  • License: MIT
  • Architecture: x86_64
  • Source Package: llama.cpp
  • 1 Abhängigkeiten
  • 1 stellt bereit
  • normalized package name match
  • Abgeglichen nach: Llama Cpp
Alpine Linux edge package indexes · dl-cdn.alpinelinux.org · Alpine Linux edge package indexes: llama-imatrix from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz

Paketgraph

Links stammen aus dem lokalen Paketbeziehungsgraph, Ergänzungen, Abhängigkeitskanten, Ecosystem-Matches und Paket-Hub-Mitgliedschaft.

Verwandte Tools

  • openssl@3Runtime dependency declared by Homebrew.
  • cmakeBuild dependency declared by Homebrew.
  • ramalamaPopular package that depends on this formula.

Gleicher Workflow

  • ollamaShares pkgdb curated category or tags: ai, cli, local-ai, model-tools.
  • mlx-lmShares pkgdb curated category or tags: ai, cli, machine-learning, model-tools.
  • rapid-mlxShares pkgdb curated category or tags: ai, cli, local-ai, model-tools.
  • shimmyShares pkgdb curated category or tags: ai, cli, local-ai, model-tools.
  • mlxShares pkgdb curated category or tags: ai, c-plus-plus, cli, machine-learning.
  • opencvShares pkgdb curated category or tags: ai, c-plus-plus, cli, machine-learning.

Quellspur

Aus Repository-Daten generiert

Diese Seite wird von av-web aus dem privaten Paket-SQLite-Artefakt bereitgestellt, das scripts/generate-pkg-sqlite.py erstellt.

Verwendete Quellen

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