llama.cpp by ggml-org

LLM inference in C/C++

llama.cpp interface screenshot from project README
ggml
Verdict 77/100 health $4.13/mo cheapest, hetzner 2/5 setup difficulty Last release 2 days ago

Self-host llama.cpp on hetzner CAX11 for $4.13/mo.

Health score
77 /100
6-dim composite
Self-hosts from
$4.13 /mo
hetzner · CAX11
Difficulty
2 /5
Docker + read README
GitHub stars
108k
18k forks

About llama.cpp

From the project's README at github.com/ggml-org/llama.cpp. Lightly cleaned for readability; for the full source see the upstream repo.

[](https://opensource.org/licenses/MIT) [](https://github.com/ggml-org/llama.cpp/releases) [](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml)

LLM inference in C/C++ Recent API changes Changelog for API Changelog for REST API Hot topics Hugging Face cache migration: models downloaded with are now stored in the standard Hugging Face cache directory, enabling sharing with other HF tools. guide : using the new WebUI of llama.cpp guide : running gpt-oss with llama.cpp [[FEEDBACK] Better packaging for llama.cpp to support downstream consumers ](https://github.com/ggml-org/llama.cpp/discussions/15313) Support for the model with native MXFP4 format h

Health score breakdown

6-dimension composite. See methodology for formula and weights.

activity
100
maturity
79
community
91
security
85
sustainability
53
adoption
45

Adoption signals

Real-world usage data, pulled from each registry. The bigger the numbers, the more battle-tested the project.

SignalValueSource
GitHub stars 108k github.com/ggml-org/llama.cpp
GitHub forks 18k github.com/ggml-org/llama.cpp

Release & maintenance

Is this project actively maintained, or about to die? Check the recency of last commit and last release.

Project age3.2 yearssince Mar 2023
Last commit2 days agoMay 4, 2026
Releases shipped5,993last: 2 days ago
Security policySECURITY.mddeclared by maintainers

Self-hosting cost across providers

Detected requirements: 4GB RAM, 40GB disk minimum. Cheapest plan per provider that meets the requirement.

ProviderPlanSpecsMonthly
hetzner CAX11 2c · 4GB · 40GB $4.13 USD Deploy →
vultr VC2 1c · 1GB · 25GB $5 USD Deploy →
linode Nanode 1GB 1c · 1GB · 25GB $5.12 USD Deploy →
digitalocean Basic Regular 1GB 1c · 1GB · 25GB $6 USD Deploy →

Security advisories

10 known advisories tracked via OSV.dev. Most recent: CVE-2026-33298.

What people say on Hacker News

Ready to self-host llama.cpp?

Spin up a hetzner CAX11 (4GB RAM, 40GB disk) for $4.13/mo and follow the project's official install docs.

Data last refreshed May 7, 2026.

Frequently asked questions

Last verified . Data refreshes every 30 minutes.