arcflare
Open model hub

Upload, share, and run AI models.

ArcFlare is the open hub for the model community. Discover models, run them with a single command, and publish your own.

arcflare run qwen2.5
Browse modelsUpload a model
Spotlightqwen2.5 · Alibaba Qwen · Apache-2.0
ArcFlare mascot
0open models0categories0licensesFreeto run
Get started

Install in one line

Runs locally with a built-in engine. Just needs Node.js 18+ — no Docker, no setup.

arcflare — install
$ 

From zero to running in one command.

Pull, load, and run any model from the hub — or publish your own — straight from your terminal. No dashboards, no boilerplate.

  • ▸ One CLI for running and sharing
  • ▸ Streaming pulls with resumable downloads
  • ▸ Runs locally — your data never leaves your machine
arcflare — zsh
$ 

Featured models

Hand-picked open models to get you started.

qwen2.5

by Alibaba Qwen

7B

Qwen2.5 is Alibaba's latest series of multilingual LLMs with strong instruction following, long context, and tool use.

chatmultilingualtools
~6 GBApache-2.0

llama3.2

by Meta

3B

Meta's compact Llama 3.2 models (1B and 3B) — efficient, on-device-friendly assistants.

chatsmalledge
~4 GBLlama 3.2 Community

deepseek-r1

by DeepSeek

7B

DeepSeek-R1 — an open reasoning model trained with reinforcement learning, with strong math and coding.

reasoningchain-of-thoughtmath
~6 GBMIT

flux.1-schnell

by Black Forest Labs

12B

FLUX.1 [schnell] — a fast, fully open (Apache-2.0) text-to-image model that generates high-quality images in just 1–4 steps.

imagetext-to-imagefast
~24 GBApache-2.0

How it works

1

Find a model

Browse the library by category, size, or capability — chat, code, vision, and more.

2

Run it locally

Pull and run any model with a single command. No accounts, no setup ceremony.

3

Share your own

Publish your fine-tunes with a model card so the community can run them too.