Skip to content
Weights Not Walls
Menu

llamafile

by mozilla-ai

In its repository's words: “Distribute and run LLMs with a single file.”

Repository on GitHubdocs.mozilla.ai/llamafile

Facts from GitHub

Licence
Apache-2.0 (Apache License 2.0), permissive, our readingGitHub's licence detection could not identify the licence file, so we read the file on 19 Nov 2026: The LICENSE file is the Apache License 2.0 notice, pointing to the full text.
Activity
Last push 9 Nov 2026: pushed to in the last 90 days
Latest release
0.10.615 Sep 2026
Stars
27k
Main language
C++
On GitHub since
10 Sep 2023
Topics
cross-platform, gguf, llama-cpp, local-ai, local-inference, local-llm, open-source-ai, single-file-executable, speech-to-text

What it says it supports

Loads
GGUF
Runs on
Linux, macOS, Windows
Hardware
CPU only

Each item is on our list for this tool and named in its README. A mention is not a test: check the project's documentation for your setup.

Reviewed models it can load

Matched by file format only, from our snapshot of the Hub: GGUF where we measured GGUF files, other formats where a conversion exists, safetensors for the original weights. Support for a new architecture can lag behind its release.

GGUF 386

openai-community/gpt2, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, baidu/Unlimited-OCR, and 374 more, most downloaded first

Other tools in Run locally

All of Run locally

Tool data from the GitHub API, fetched 19 Nov 2026, 15:35 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.