Distribute and run LLMs with a single file.
llamafile lets you distribute and run LLMs with a single file.
Our goal is to make open LLMs much more accessible to both developers and end users. We're doing that by combining llama.cpp with Cosmopolitan Libc into one framework that collapses all the complexity of LLMs down to a single-file executable (called a "llamafile") that runs locally on most computers, with no installation.
What's Changed
- Update llama.cpp to b10441 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1043
- llamafile_open_zip: validate the zip entry window against the actual file size by @professor-moody in https://github.com/mozilla-ai/llamafile/pull/1039
- fix(zip): guard extra-field header read before bounds are known by @shoemoney in https://github.com/mozilla-ai/llamafile/pull/1044
- fix(build): add missing link recipes for llama-bench, quantize, imatrix and perplexity by @dexhunter in https://github.com/mozilla-ai/llamafile/pull/1034
- fix(build): compile the ggml objects with -DNDEBUG by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1050
- Enable -DGGML_CUDA_USE_GRAPHS / -DGGML_HIP_GRAPHS by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1051
- fix(ggml): use ggml_time_init() in ggml_time_ms and ggml_time_us so that timer_freq is initialised by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1054
- Vulkan toolchain by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1055
New Contributors
- @professor-moody made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1039
- @shoemoney made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1044
- @dexhunter made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1034
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.5...0.10.6
| Publisher | Mozilla Ocho |
|---|---|
| Version | 0.10.6 |
| Release date | 2026-09-15 |
| License | Apache-2.0 |
| Installer type | portable |
| Architecture | x64 |
| Package ID | Mozilla.llamafile |
Install llamafile from the command line with Windows Package Manager (winget):
winget install --id=Mozilla.llamafile -e
The AI coding agent built for the terminal.
The AI Code Editor
Ship 100x With The Agent IDE
Unleash Claude’s raw power directly in your terminal. Search million-line codebases instantly. Turn hours-long workflows into a single command. Your tools. Your workflow. Your codebase, evolving at th
The object store for AI data infrastructure.
Codex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.
Experience liftoff with the next-gen agent platform.
Discover, download, and run local LLMs