llama.cpp
Project record
Maintained by ggml team at Hugging Face (ggml.ai, acquired by Hugging Face in 2026), with the ggml-org community786
llama.cpp is a C/C++ library and set of tools for running LLM and vision-language model inference locally or in the cloud, built on the ggml tensor library. It supports integer quantization and many hardware backends. It includes a command-line interface and an OpenAI-compatible server.2
- Repository: Repository (external site: github.com)
- Website: Website (external site: llama.app)
- License: LICENSE (external site: github.com)
- Release notes: Releases (external site: github.com)
Availability and license
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Unknown — no complete fact-level rights review
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | 1 |
| DocumentationIs user documentation published? | Public | Documentation is kept in the repository README and docs directory.2 |
| InstallationAre installation instructions or packages publicly available? | Public | The README documents an install script on llama.app, Docker images, prebuilt binaries on the releases page, and building from source.2 |
| Supported platformsAre supported operating systems or hardware documented? | Public | The README lists CPU and GPU backends including Metal, CUDA, HIP, Vulkan, SYCL, and MUSA. Releases include prebuilt binaries for macOS, Linux, Windows, and Android.24 |
| Release statusAre versioned releases published? | Public | Versioned (v0.x) releases and frequent numbered builds are published on GitHub.4 |
What it is useful for
Organization context
Provenance and derivatives
Catalog records that name this entry in their provenance:
U.S. eligibility
Eligible · basis: U.S.-governed project
ggml.ai, the company Georgi Gerganov founded in 2023 to support ggml development, says it was acquired by Hugging Face in 2026. Hugging Face's February 20, 2026 announcement says the ggml team joined Hugging Face, dedicates all of its time to maintaining llama.cpp, and keeps leadership of the project's technical direction, while the project stays open source and community driven. The documented maintaining entity is therefore the ggml team within Hugging Face, a U.S. company in this catalog. NVIDIA's pending agreement to acquire Hugging Face would not change the U.S. basis. Eligibility rests on this documented ownership and maintenance, not on contributors' nationality.7869
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.