✨ new: inference.sh 0.1 is out!

run ai on your machine

the easiest way to run open models like wan, flux, deepseek, magi, and more on your own machine.

by using inference.sh, you agree to its terms of use

we have an app for bagel

discover and deploy pre-built ai models with just a few clicks

intuitive chat interface

chat with multiple models at once

a curated chat interface with the most popular open llm models

You
Gemma 3
Qwen 3
DeepSeek R1

boost inference speed with remote GPUs

instantly switch to powerful rented remote GPUs from 40+ providers.

Diffusion
Step 1 / 50
GPU:NVIDIA 4080 (16GB VRAM)
Steps/s0.10
VRAM%95%
CPU%92%

a radically better way to run ai models

our opinionated approach to ai workflows is fast and easy to use.

run new ai apps in seconds, not hours.

everything you need to run ai applications at the speed of light.

100+ ready apps

plug & play ai components for image, video, llm & audio. build powerful workflows in minutes.

100+

install in one line

install inference.sh in one line in the terminal and run ai apps in seconds.

1

10x better workflows

build advanced ai workflows with 10 nodes instead of 100. skip the complexity.

10x
replace comfyui

running on your local machine?
we are free to use!

we want to empower the creative community. that's why we're free to use on your local hardware.

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.