llama.cpp

By ggml ยท Local and open models

About llama.cpp

Open-source C/C++ engine for running open models efficiently on ordinary hardware, used inside many local AI tools.

Details

  • Free plan or free version

    Yes

  • Open source

    Yes

  • Can run on your own servers or machine

    Yes

Not enough info yet on works in VS Code, works in JetBrains IDEs. Check the tool's own site.

Listing written by CodeBan, checked 2026-11-03. Report a correction or request removal. Back to local and open models.

More tools in local and open models

Ollama

Runs open models on your own computer with one command and serves them through a local API that editors can use.

  • Free plan or free version
  • Open source
  • Can run on your own servers or machine

LM Studio

Desktop app for finding, downloading and chatting with open models locally, with a local server other tools can call.

  • Free plan or free version
  • Can run on your own servers or machine

Tabby

by TabbyML

Open-source, self-hosted coding assistant that gives a team code completion and chat on its own servers.

  • Open source
  • Can run on your own servers or machine
  • Works in VS Code

Hugging Face

Hub for open models and datasets, where most open code models are published, with tools to run and deploy them.

  • Free plan or free version