Free
Added on Oct 25,2026
Llama is a free, open-source app from the llama.cpp team and Hugging Face that runs open AI models locally on Windows 11 and Mac, with a command-line option for Linux. On Windows it sits in the system tray as one local AI server shared by all your apps.
Users can download open models from Hugging Face in one click, chat with any installed model from a quick-access window, and connect other apps through a local API. It works offline and needs no configuration to get started.
The local API runs at a localhost address and speaks the OpenAI API, so apps that support OpenAI can use it by changing the base URL. Anthropic-compatible endpoints are also provided, along with streaming, tool calling, structured output and vision.
Llama checks your hardware and automatically picks settings such as quantisation, context size, image input, speculative decoding and batch size. All llama.cpp settings remain available in a plain-text file.
Models are stored once in the Hugging Face cache and shared with other tools, and they unload after five minutes idle. Coding agents, editors, scripts and other apps can share Llama's engine and models rather than bundling their own.
Recommended models named on the site include Gemma 4, GPT-OSS 20B and Qwen 27B, matched to the memory available on your machine. A llama command offers subcommands such as cli and serve, and the API can be reached from other devices over Tailscale.
Pricing: Llama is free and open source.
It is suited to developers, privacy-minded users and anyone who wants to run AI models on their own computer for chat, coding agents or offline AI features in their own apps.
Similar tools to compare with Llama:
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| NSFW JS | Free | Web developers who need to pre-screen user-uploaded images in the browser before they reach their servers. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Own Llama? Add this badge to your website.
Leave a review for the community
No Review Found
