llamafile

Verified ✅ Truly Free

Distribute and run LLMs as a single executable file. llamafile combines llama.cpp with Cosmopolitan Libc so the same file runs on Windows, macOS and Linux. The project moved to mozilla-ai/llamafile; version 0.10.6 (September 2026) tracks a recent llama.cpp with CUDA/HIP graphs and Vulkan support.

Single File Cross Platform Mozilla Server
Get API Key Suggest Edit
638

Overview

Provider Type

Local

API Endpoint

http://localhost:8080/v1

Free Tier Highlights

Hardware dependent

Why Choose llamafile?

llamafile packs an LLM and llama.cpp into one executable that runs on Windows, macOS and Linux, with nothing to install.

Best for: sharing a model as a single file, or running one on a machine you don't control.

Watch out: the bundled example models are old; pick a recent GGUF.

Quick Start Guide

1

Download a .llamafile from HuggingFace

2

Open terminal

3

Run ./model.llamafile

4

Open browser at localhost:8080

Available Models

3 free models
Model Name ID Context Capabilities
LLaVA 1.5 Free
llava-1.5-7b-q4
Local
Vision
Mistral 7B Free
mistral-7b-instruct-v0.2.Q4_K_M
Local
-
TinyLlama Free
tinyllama-1.1b-chat-v1.0.Q8_0
Local
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

# Run: ./model.llamafile --server
client = OpenAI(
    api_key="llamafile",
    base_url="http://localhost:8080/v1"
)

response = client.chat.completions.create(
    model="local",
    messages=[
        {"role": "user", "content": "What is llamafile?"}
    ]
)

print(response.choices[0].message.content)

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Hardware dependent

Daily Quota

Requests per day

Unlimited

Token Limit

Tokens per minute

Unlimited

Monthly Quota

Per month limit

Free Open Source

Use Cases

Sharing models easily

Archiving models

Quick local testing

Education/Demos

Limitations & Considerations

File sizes are large (contain weights)

CLI usage often required

Windows requires appending .exe

Beta software

Community Hub

Live

Join the discussion, share tips, and rate llamafile.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using llamafile

Start Building Now