# llamafile

> Package a model and runtime into one executable that runs on most operating systems.

Canonical: https://thelocalbench.com/tools/llamafile · Data as of 2026-10-12 · The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0

Flags: [verified] checked against primary source · [sourced] cited · [estimate] formula · [sample] placeholder

- Category: Runtimes / Single-file runtime
- Website: https://docs.mozilla.ai/llamafile
- Repository: https://github.com/mozilla-ai/llamafile
- Open source: yes, Apache-2.0 [verified] https://github.com/mozilla-ai/llamafile/blob/HEAD/LICENSE
- Pricing: free, starting $0 [verified] https://github.com/mozilla-ai/llamafile
- Platforms: macOS, Windows, Linux [sourced] https://github.com/mozilla-ai/llamafile#readme
- Added 2026-10-13, last verified 2026-10-13
- Sponsored: no

## Works with local models

| Integration | Status | Flag | Source |
|---|---|---|---|
| Ollama | not yet confirmed | [not_measured] |  |
| llama.cpp | yes | [sourced] | https://github.com/mozilla-ai/llamafile#readme |
| LM Studio | not yet confirmed | [not_measured] |  |
| OpenAI-compatible | not yet confirmed | [not_measured] |  |
| MCP | not yet confirmed | [not_measured] |  |

JSON: https://thelocalbench.com/api/v1/tools/llamafile.json

Logo: trademark of its owner, shown to identify the tool (source: apple-touch-icon, https://docs.mozilla.ai/llamafile/~gitbook/icon?size=medium&theme=light&border=false).