| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| zipalign-0.10.3 | 2026-06-02 | 851.5 kB | |
| whisperfile-0.10.3 | 2026-06-02 | 5.4 MB | |
| llamafile-0.10.3.zip | 2026-06-02 | 248.9 MB | |
| llamafile-0.10.3-thin | 2026-06-02 | 44.1 MB | |
| llamafile-0.10.3 | 2026-06-02 | 320.1 MB | |
| diffusionfile-0.10.3 | 2026-06-02 | 73.9 MB | |
| llamafile v0.10.3 source code.tar.gz | 2026-06-02 | 14.5 MB | |
| llamafile v0.10.3 source code.zip | 2026-06-02 | 14.9 MB | |
| README.md | 2026-06-02 | 823 Bytes | |
| Totals: 9 Items | 722.8 MB | 14 | |
What's Changed
This release is mainly a bugfix to a regression introduced in 0.10.2 (many many thanks to @niutech for opening the issue! 🙏)
As releases become more frequent, we are working to better automate the process and making this more open. This PR brings a new llamafile/release.sh script that's the one used to create all the new release files (we'll be testing it until the next release before updating the RELEASE.md doc).
- Update release scripts by @aittalam in https://github.com/mozilla-ai/llamafile/pull/990
- Fix uncaught SIGSEGV when GPU init fails, restore CPU fallback (#988) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/989
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.2...0.10.3