Send a request

llama.cpp

by ggml

Language models on your laptop, even without a GPU

The fast C/C++ inference engine behind many local AI apps — runs even on laptops without a GPU.

Open SourceTrust 91For prosRuns offlinemacOS · Windows · Linux
Get it via OROBO

Checked sourcegithub.com/ggml-org/llama.cppLicence: MITchecked 19 hours agoGitHub lists a SHA-256 checksum for every release file.

Have it set up for you instead:Request setup by OROBOOr start with the AI Compass: a written assessment at a fixed price of €490 (businesses only).

How it runs for you

Simulation starting …

Illustration, not a real test run

What you get

What you get

  1. 01Run open models locally, no cloud needed
  2. 02Browser chat and an OpenAI-compatible API included
  3. 03Runs on CPUs, Apple silicon and graphics cards

For you if …

  • Developers building local AI into their apps
  • Tinkerers testing models on their own hardware

Pick something else if …

  • Prefer clicking to typing? Try LM Studio or Jan

How to start

In three steps.

What you need
  • Mac, Windows or Linux
  • No GPU required
  • RAM to match the model
  • Comfort with the terminal
  1. 1Install with brew install llama.cpp or grab a release from GitHub
  2. 2Start a model: llama-server -hf ggml-org/gemma-3-1b-it-GGUF
  3. 3Open http://localhost:8080 and chat in your browser

Safety check

6 of 7 checks passed · 1 note

actively maintainedLicence: MIT

Trust 91
Who is behind it?
  • Taken by OROBO from the official source. The maker has not joined OROBO yet.
Is the code clean?
  • Source code publicly visible
  • Licence: MIT
  • Review code pattern: Install script piped to shell from llama.app
Is it maintained?
  • Website reachable
  • Updated today
Technical details & what we don’t check
  • Website loads fast
  • Website protection settings: 5 of 6 (website only, not the software)HSTS, CSP, nosniff, Frame-Schutz, Referrer-Policy

We automatically check origin, code patterns, licence, maintenance and reachability — again every day. We do not check whether the software fits your purpose, how it handles your data, or whether it works without errors. Last checked 19 hours ago. How OROBO checks

Alternatives for the same goal

OllamaBuild it yourself · OllamaRun language models locally with one commandOpen SourceTrust high, 97Runs offlineJanUse right away · Menlo ResearchAn AI assistant that runs on your own computerOpen SourceTrust high, 100Runs offlineOpen WebUIUse right away · Open WebUIAn AI chat for your team, on your own serverOpen SourceTrust high, 97Runs offlineLM StudioUse right away · Element LabsFind, download and run open AI models locallyFreeLimited checks · 3 checksRuns offlineGPT4AllUse right away · Nomic AIAI chat that runs offline on your computerOpen SourceTrust high, 91Runs offlineTransformersBuild it yourself · Hugging FaceThousands of open AI models in a few lines of codeOpen SourceTrust high, 100Runs offlinewhisper.cppBuild it yourself · ggmlTurn recordings into text, right on your machineOpen SourceTrust high, 100Runs offlineLangChainBuild it yourself · LangChainConnect models, tools and data into an AI appOpen SourceTrust high, 97For developers

Facts

AreaBuild it yourself
PriceOpen Source
LicenceMIT
Runs onmacOS, Windows, Linux
Popular with developers★ 133.4K GitHub
Last updated04 Nov 2026
Sourceggml-org/llama.cpp ↗
I am the maker