Added Oct 28, 2026
llamafile
FreePackage an LLM and its runtime into one portable executable file
What is llamafile?
llamafile is an open-source project from Mozilla.ai that bundles model weights and a llama.cpp-based runtime into a single executable. The same file runs on macOS, Windows, Linux and BSD, so sharing a local model is as simple as sending one file.
It uses Cosmopolitan Libc to build one binary for several operating systems and CPU types, and starts a local chat UI and API server when run. Version 0.10 rebuilt the core and restored GPU support for CUDA and Metal.
llamafile is free under the Apache 2.0 license. Prebuilt llamafiles for popular open models are available to download, and you can build your own from any GGUF file.
Features
- Single-file executables
- Cross-platform binaries
- Built-in chat UI
- Local API server
- GPU acceleration
Tags
Releases
+ Submit new release- Listed
llamafile was added to the directory.
Organization
Mozilla.ai
🇺🇸 United States
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Free
- Paid options from
- 100% free
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top llamafile alternatives
View allModels & APIs
Run open models locally with one command, plus optional cloud models
Models & APIs
Apple's array framework for running and training models on Apple Silicon
Models & APIs
Gradio web interface for running local LLMs with many backends
Compare llamafile
If you liked llamafile
- OpenJarvisNew
Open-source framework for personal AI agents that run on your own device
FreeAgents & automation118 views97 clicks to the websiteMade in United States Free open-source desktop client for dozens of AI providers
FreeChat assistantsMade in China
Pros and cons
Pros
- No install or dependencies
- Runs on many systems
- Great for sharing models
Cons
- Large file sizes
- Fewer features than full apps
- Updates lag llama.cpp
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is llamafile?
llamafile is an open-source project from Mozilla.ai that bundles model weights and a llama.cpp-based runtime into a single executable. The same file runs on macOS, Windows, Linux and BSD, so sharing a local model is as simple as sending one file.
How much does llamafile cost?
llamafile is 100% free.
Is there a free version of llamafile?
Yes. llamafile is completely free to use.
What are the main features of llamafile?
Single-file executables, Cross-platform binaries, Built-in chat UI, Local API server, GPU acceleration.
Who makes llamafile?
llamafile is made by Mozilla.ai.
What are the best alternatives to llamafile?
Popular alternatives include Ollama, llama.cpp, MLX.