mozilla-ai/llamafile

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

26224 stars · 1650 forks observed · 2026-10-12

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-12, confidence 0.97

Llamafile packages LLMs and Whisper models into a single, portable executable. It runs locally on most operating systems without any installation or dependencies.

Use cases

• run a large language model locally without installing Python or CUDA
• transcribe audio files to text on any desktop OS using a single binary
• experiment with different quantized GGUF models for edge devices
• deploy a self‑contained LLM service on a Raspberry Pi or other low‑power hardware
• create a portable AI tool that can be shared via a simple file download

When to choose

• You need zero‑install, cross‑platform AI inference on CPUs only
• You prefer a single binary that can be versioned and distributed easily
• You want to run both LLM chat and speech‑to‑text locally without internet access

When to avoid

• You require GPU acceleration or advanced CUDA features
• You need a full‑stack serving platform with scaling, monitoring, and orchestration
• You depend on a package manager or language‑specific ecosystem for integration

Facets

cli-tool · maturity active

llm-inference speech-recognition artificial-intelligence large-language-models speech-processing windows bsd cli single-file-executable local-inference gguf llama-cpp whisper-cpp cosmopolitan-libc linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mozilla-ai/llamafile")