llamafile
About llamafile
llamafile is a tool designed to simplify the distribution and execution of large language models (LLMs) by packaging them into a single executable file. It combines llama.cpp with Cosmopolitan Libc to create portable executables that run locally on various operating systems and CPU architectures without requiring installation.
The project also includes whisperfile, a single-file speech-to-text tool based on whisper.cpp, offering transcription and translation capabilities across multiple platforms. llamafile is developed as part of Mozilla.ai's initiative to make open LLMs more accessible to both developers and end users.
Key features
- Distributes and runs LLMs with a single executable file
- Includes whisperfile for speech-to-text functionality
- Runs locally on most operating systems and CPU architectures
- No installation required
- Supports transcription and translation of audio files
- Compatible with various pre-built models
Download 0.10.3
Jun 2, 2026No direct download assets detected for the latest release.
View all 10 versionsFrequently asked questions
- Is llamafile free?
- Yes. llamafile is free and open-source software, distributed under the NOASSERTION license.
- What is the latest version of llamafile?
- The latest version is 0.10.3, released on Jun 2, 2026.
- What is llamafile?
- llamafile is a tool that packages large language models into a single executable file, making them easy to distribute and run locally without installation.
- How do I run a llamafile?
- Download a llamafile, make it executable (on macOS/Linux/BSD), and run it directly. Windows users need to rename the file to add .exe before running.
- What platforms are supported?
- llamafile runs on most operating systems and CPU architectures. However, Windows has a 4GB file size limit for executables.
- What license does llamafile use?
- The llamafile project is licensed under Apache 2.0, while modifications to llama.cpp and whisper.cpp are MIT-licensed.
More AI & LLM Tools
ollama
ollama
Ollama provides access to a variety of AI and large language models, including Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, and Gemma. It simplifies the process of setting up and using these models for various applications.
dify
langgenius
Dify is a production-ready platform for developing agentic workflows. It supports AI and LLM tools for streamlined workflow creation.
anything-llm
Mintplex-Labs
AnythingLLM is a local-first AI tool for running language models independently. It provides a self-hosted alternative to cloud-based solutions for users seeking full control over their AI agents.