llama.cpp

llama.app AI Chatbots & Assistants Online toolOpen source

llama.cpp runs open models locally on a computer through the llama.cpp project.

llama.app
llama.cpp homepage screenshot

About llama.cpp

llama.cpp provides an app for Mac and Windows that runs open models on the computer. Users can chat with models in a browser through Open chat, or connect coding agents, editors, and scripts to a local API at localhost:9931/v1 that works with OpenAI-compatible tools. The app selects model settings based on the computer, stores each model once in the Hugging Face cache, and works offline. Linux is supported through a command-line install, and models load on request and unload after 5 minutes idle.

Key features

  • Chat with downloaded models in browser via Open chat
  • Local API at localhost:9931/v1 for agents and editors
  • One-click model install with automatic memory-based settings
  • Shared Hugging Face cache so each model stored once
  • Models load on request and unload after 5 minutes idle
  • Command-line install option for Linux and plain-text settings file
Best for: People who want to run open models on their own computer and use them from chat and coding tools.
Good for
  • Works offline according to homepage description
  • Open source with public GitHub repository
  • Automatically selects settings based on computer memory
Watch out for
  • Desktop app described for Mac and Windows 11; Linux uses command-line version
  • Model use depends on available memory and disk space for the selected model

llama.cpp at a glance

Website
llama.app
Type
Online tool
Pricing
Not confirmed. Check the site
Platforms
Web
Open source
Yes · Source code
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

llama.cpp alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Chatbots & Assistants

Well-known listings from the same topic.

All 238

llama.cpp FAQ

How do apps connect to Llama?
Point apps that work with OpenAI to localhost:9931/v1.
How is Llama installed on Linux?
Run: curl -LsSf https://llama.app/install.sh | sh
Where are models stored?
In the Hugging Face cache, shared with llama.cpp and other tools.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing