llamafile: Releases and Overview
Packages model weights and llama.cpp into one executable that runs on any OS without installation.
Category: Inference engines and runtimes. Part of our engine and tool tracker.
At a Glance
| Item | Value |
|---|---|
| Repository | Mozilla-Ocho/llamafile |
| License | NOASSERTION |
| Main language | C++ |
| GitHub stars | 25,978 (as of 2026-09-17) |
| Latest release | 0.10.6 (2026-09-16) |
| Install / docs | official documentation |
The project describes itself as: “Distribute and run LLMs with a single file.”
Release History
Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.
| Version | Released | Release notes | Our article |
|---|---|---|---|
| 0.10.6 | 2026-09-16 | GitHub | — |
| 0.10.5 | 2026-08-03 | GitHub | — |
| 0.10.4 | 2026-07-17 | GitHub | — |
| 0.10.3 | 2026-06-03 | GitHub | — |
| 0.10.2 | 2026-05-30 | GitHub | — |
| 0.10.1 | 2026-05-02 | GitHub | — |
| 0.10.0 | 2026-03-19 | GitHub | — |
| 0.9.3 | 2025-05-15 | GitHub | — |
| 0.9.2 | 2025-04-04 | GitHub | — |
| 0.9.1 | 2025-03-11 | GitHub | — |
| 0.9.0 | 2025-01-06 | GitHub | — |
| 0.8.17 | 2024-12-01 | GitHub | — |
| 0.8.16 | 2024-11-02 | GitHub | — |
| 0.8.15 | 2024-10-31 | GitHub | — |
| 0.8.14 | 2024-10-14 | GitHub | — |
| 0.8.13 | 2024-08-19 | GitHub | — |
| 0.8.12 | 2024-07-28 | GitHub | — |
| 0.8.11 | 2024-07-24 | GitHub | — |
| 0.8.10 | 2024-07-24 | GitHub | — |
| 0.8.9 | 2024-07-02 | GitHub | — |
| 0.8.8 | 2024-06-30 | GitHub | — |
| 0.8.7 | 2024-06-25 | GitHub | — |
| 0.8.6 | 2024-05-25 | GitHub | — |
| 0.8.5 | 2024-05-25 | GitHub | — |
| 0.8.4 | 2024-05-10 | GitHub | — |
| 0.8.2 | 2024-05-10 | GitHub | — |
| 0.8.1 | 2024-04-27 | GitHub | — |
| 0.8 | 2024-04-25 | GitHub | — |
| 0.7.4 | 2024-04-25 | GitHub | — |
| 0.7.3 | 2024-04-20 | GitHub | — |
| 0.7.2 | 2024-04-20 | GitHub | — |
| 0.7.1 | 2024-04-13 | GitHub | — |
| 0.7 | 2024-03-31 | GitHub | — |
| 0.6.2 | 2024-01-28 | GitHub | — |
| 0.6.1 | 2024-01-20 | GitHub | — |
| 0.6 | 2024-01-09 | GitHub | — |
| 0.5 | 2024-01-06 | GitHub | — |
| 0.4.1 | 2023-12-28 | GitHub | — |
| 0.4 | 2023-12-14 | GitHub | — |
| 0.3 | 2023-12-12 | GitHub | — |
| 0.2.1 | 2023-12-02 | GitHub | — |
| 0.2 | 2023-12-02 | GitHub | — |
| 0.1 | 2023-11-21 | GitHub | — |
Articles on Local Model Watch
No articles yet.
Last updated 2026-09-18 (JST). Facts above come from the GitHub API; the one-paragraph summary is written by the site’s editors.