How to use Llamafile: what you can do with it

3 use cases

• Run a local LLM from a single file

  Download a prebuilt Llamafile, make it executable and chat with a model offline.

  • REPO mozilla-ai/llamafile
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Beginner
  View prompt

  Download the mozilla-ai/llamafile Qwen3.5 0.8B example, make it executable and run it. Then ask it <question> and tell me how fast it answered on this machine.

  Share Email me this

• Hand a model to a colleague as one file

  Package a model as a Llamafile so anyone can run it without setting up a runtime.

  • REPO mozilla-ai/llamafile
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Intermediate
  View prompt

  Following the mozilla-ai/llamafile Creating llamafiles docs, package <model> as a llamafile for my teammate. Test that it starts on <OS> and write them a two line note on how to run it.

  Share Email me this

• Transcribe audio locally with whisperfile

  Use whisperfile, the single-file speech-to-text tool bundled with Llamafile, to transcribe recordings offline.

  • REPO mozilla-ai/llamafile
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Beginner
  View prompt

  Following the mozilla-ai/llamafile whisperfile docs, set up whisperfile and transcribe <audio file> locally. Save the transcript as <name>.txt and note any sections that came out unclear.

  Share Email me this

Quick start with Llamafile

1. Check you have what it needs: macOS, Linux, BSD or Windows on most CPU architectures; Disk space and RAM for the model you download; On Windows, only executables under 4GB run directly.
2. Open mozilla-ai/llamafile on GitHub and read the README and license.
3. Download the example model with curl -LO https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile
4. Make it executable with chmod +x Qwen3.5-0.8B-Q8_0.llamafile on macOS, Linux or BSD
5. Run it with ./Qwen3.5-0.8B-Q8_0.llamafile
6. On Windows, rename the file to add the .exe extension before running

These steps come from our top use case, Run a local LLM from a single file, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for mozilla-ai/llamafile

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forDevelopers and curious users who want to run an open LLM locally, or hand a model to someone else, without installing a runtime.
• Why it is hot27k stars, talked about in 2 AI sources we track
• LanguageC++
• Sourcegithub.com/mozilla-ai/llamafile · Back to Hot repos

Requirements

• macOS, Linux, BSD or Windows on most CPU architectures
• Disk space and RAM for the model you download
• On Windows, only executables under 4GB run directly

Related repos

• Trended earlier REPO ggml-org/llama.cpp llama.cpp llama.cpp is a dependency-free C/C++ engine for running LLMs and vision language models locally or in the cloud, with quantization, many GPU backends, a CLI and an OpenAI-compatible server.
• Trended earlier REPO goccy/go-llama Go Llama go-llama is a Go library that runs GGUF language models through llama.cpp compiled to WebAssembly and translated to Go, with no cgo or shared library needed.
• Trended earlier REPO google-ai-edge/LiteRT-LM LiteRT LM LiteRT-LM is Google's production-ready orchestration layer for running LLMs with LiteRT on device. It runs on Android, iOS, web, desktop and IoT boards such as Raspberry Pi, uses GPU and NPU acceleration, supports vision and audio inputs and function calling, and handles Gemma, Llama, Phi-4, Qwen and more. It powers on-device AI in Chrome, Chromebook Plus and Pixel Watch, and ships a CLI plus Python, Kotlin, Swift, JavaScript and C++ APIs.