How do I deploy a repo from the Hub?

In the Runpod console, go to the Hub page, browse or search for a repo that matches your needs, review details including hardware requirements and configuration options, then click Deploy and Create Endpoint. Within minutes, you’ll have a live Serverless endpoint you can call via API. For more details, see https://docs.runpod.io/hub/overview.

Runpod Hub | The fastest way to fork and deploy open-source AI

Built for open source.

Discover, fork, and contribute to community-driven projects.

One-click deployment.

Skip the setup—launch any package straight from GitHub.

Autoscaling endpoints.

Deploy autoscaling endpoints from community templates.

How it Works

From code to cloud.

Deploy, scale, and manage your entire stack in one streamlined workflow.

Public endpoints

Access ready-to-use public AI endpoints.

Test, integrate, and deploy without provisioning your own infrastructure.

deep-cogito / Deep Cogito v2 Llama 70B

The Deep Cogito v2 Llama 70B model is part of a groundbreaking family of open-source hybrid reasoning LLMs developed under a novel AI paradigm

Text to Text

qwen / Qwen Image

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing.

Text to Image

qwen / Qwen3 32B AWQ

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

Text to Text

minimax / Minimax Speech 02 HD

MiniMax is a high-definition text-to-speech model

Text to Audio

qwen / Qwen Image LoRA

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing and has LoRA support.

Text to Image

qwen / Qwen Image Edit

The image editing version of Qwen-Image. Qwen-Image-Edit successfully extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing.

Image to Image

Bytedance / Seedance 1.0 pro

Latest high-performance video generation model, featuring multi-shot storytelling, strong instruction-following, and semantic understanding.

Image to Video

Bytedance / Seedream 3.0

Seedream 3.0, a native high-resolution bilingual image generation foundational model (Chinese-English).

Text to Image

Alibaba / Wan 2.2 I2V 720p

Wan 2.2 is an open-source AI video generation model that utilizes a diffusion transformer architecture and a novel 3D spatio-temporal VAE (Wan-VAE) for image-to-video generation.

Image to Video

Alibaba / Wan 2.2 T2V 720p

Wan 2.2 is an open-source AI video generation model that utilizes a diffusion transformer architecture and a novel 3D spatio-temporal VAE (Wan-VAE).

Text to Video

black-forest-labs / FLUX.1 Kontext [dev]

FLUX.1 Kontext [dev] is a 12 billion parameter rectified flow transformer capable of editing images based on text instructions.

Image to Image

Alibaba / Wan 2.1 I2V 720p

Wan 2.1 is an open-source AI video generation model that utilizes a diffusion transformer architecture and a novel 3D spatio-temporal VAE (Wan-VAE) for image-to-video generation.

Image to Video

Alibaba / Wan 2.1 T2V 720p

Wan 2.1 is an open-source AI video generation model that utilizes a diffusion transformer architecture and a novel 3D spatio-temporal VAE (Wan-VAE).

Text to Video

black-forest-labs / FLUX.1 Schnell

Fastest and most lightweight FLUX model, ideal for local development, prototyping, and personal use.

Text to Image

black-forest-labs / FLUX.1 [dev]

Offers exceptional prompt adherence, high visual fidelity, and rich image detail.

Text to Image

Browse more

Community

Join the community.

Build, share, and connect with thousands

Dean Jones

Runpod has great prices as well

casper_hansen_

Why is Huggingface not adding RunPod as a serverless provider? RunPod is 10-15x cheaper for serverless deployment than AWS and GCP

DrRogerThomp

Trained a 7B parameter model in just 90 minutes for $0.80 using LoRA + Runpod. Yes, it’s possible—and no, you don’t need enterprise hardware.

Mascobot

Apparently, we got a Kaggle silver medal in the @arcprize for being in position 17th out of 1430 teams 🙃 I wish I had more time to spend on it; we worked on it for a couple of weeks for fun with limited compute (HUGE thanks to @runpod_io!)

SaaS Wiz

I love runpod

jzlegion

ai engineering is just tweaking config values in a notebook until you run out of runpod credits

Dwayne

Just discovered @runpod_io 🤯🤯🤯 Per second billing for serverless GPU capacity?! Infinitely scalable?! Whaaaat

abacaj

Runpod support > lambdalabs support. For on demand GPUs runpod still works the best ime

rachel

thank u runpod i was doing a training run for work when GCP and cloudflare died 🙏🙏 i appreciate u staying online it finished successfully

SuperHumanEpoch

I have been testing work with @runpod_io last 2 weeks and I've to say the service is pretty amazing. Super awesome UX and DevEX (and plenty of GPU backend choices). It's about ~20% pricier than Lambda labs, but worth it IMO given all the harness and workflow they provide that Lambda doesn't. I'm not associated with them in any way or manner, btw. Just a very happy customer.

DataEatsWorld

Thanks @runpod_io, loving all of the updates! 👀

skypilot_org

🏃 RunPod is now available on SkyPilot! ✈️ Get high-end GPUs (3x cheaper) with great availability: sky launch --gpus H100 Great thanks to @runpod_io for contributing this integration to join the Sky!

AlicanKiraz0

Runpod > Sagemaker, VertexAi, AzureML

dfranke

Shoutout to @runpod_io as I work through my first non-trivial machine learning experiment. They have exactly what you need if you're a hobbyist and their prices are about a fifth of the big cloud providers.

SkotiVi

For anyone annoyed with Amazon's (and Azure's and Google's) gatekeeping on their cloud GPU VMs, I recommend @runpod_io None of the 'prove you really need this much power' bs from the majors Just great pricing, availability, and an intuitive UI

YuvrajS9886

Introducing SmolLlama! An effort to make a mini-ChatGPT from scratch! Its based on the Llama (123 M) structure I coded and pre-trained on 10B tokens (10k steps) from the FineWeb dataset from scratch using DDP (torchrun) in PyTorch. Used 2xH100 (SXM) 80GB VRAM from Runpod

Yoeven

The @runpod_io event was amazing! One reason we can boast about fast speeds at @jigsawstack is because the cold boot on runpod GPUs is basically nonexistent!

winglian

Axolotl works out of the box with @runpod_io's Instant Clusters. It's as easy as running this on each node using the Docker images that we ship.

berliangor

i'm a big fan of @runpod_io they're most reliable GPU provider for training and running your models at scale

qtnx_

1.3k spent on the training run, this latest release would not have been possible without runpod

othocs

@runpod_io is so goated, first time trying it today and it’s super easy to setup + their ai helper on discord was very helpful If you ever need cpus/gpus I recommend it!

Pauline_Cx

I'm proud to be part of the GPU Elite, awarded by @runpod_io 😍

oliviawells

Needed a GPU for a quick job, didn’t want to commit to anything long-term. RunPod was perfect for that. Love that I can just spin one up and shut it down after.

skypilot_org

jzlegion

ai engineering is just tweaking config values in a notebook until you run out of runpod credits

othocs

@runpod_io is so goated, first time trying it today and it’s super easy to setup + their ai helper on discord was very helpful If you ever need cpus/gpus I recommend it!

AlicanKiraz0

Runpod > Sagemaker, VertexAi, AzureML

qtnx_

1.3k spent on the training run, this latest release would not have been possible without runpod

Mascobot

Dean Jones

Runpod has great prices as well

SkotiVi

abacaj

Runpod support > lambdalabs support. For on demand GPUs runpod still works the best ime

Yoeven

The @runpod_io event was amazing! One reason we can boast about fast speeds at @jigsawstack is because the cold boot on runpod GPUs is basically nonexistent!

berliangor

i'm a big fan of @runpod_io they're most reliable GPU provider for training and running your models at scale

rachel

thank u runpod i was doing a training run for work when GCP and cloudflare died 🙏🙏 i appreciate u staying online it finished successfully

SaaS Wiz

I love runpod

oliviawells

Needed a GPU for a quick job, didn’t want to commit to anything long-term. RunPod was perfect for that. Love that I can just spin one up and shut it down after.

Dwayne

Just discovered @runpod_io 🤯🤯🤯 Per second billing for serverless GPU capacity?! Infinitely scalable?! Whaaaat

DrRogerThomp

Trained a 7B parameter model in just 90 minutes for $0.80 using LoRA + Runpod. Yes, it’s possible—and no, you don’t need enterprise hardware.

winglian

Axolotl works out of the box with @runpod_io's Instant Clusters. It's as easy as running this on each node using the Docker images that we ship.

casper_hansen_

Why is Huggingface not adding RunPod as a serverless provider? RunPod is 10-15x cheaper for serverless deployment than AWS and GCP

SuperHumanEpoch

DataEatsWorld

Thanks @runpod_io, loving all of the updates! 👀

Pauline_Cx

I'm proud to be part of the GPU Elite, awarded by @runpod_io 😍

YuvrajS9886

dfranke

abacaj

Runpod support > lambdalabs support. For on demand GPUs runpod still works the best ime

DrRogerThomp

Trained a 7B parameter model in just 90 minutes for $0.80 using LoRA + Runpod. Yes, it’s possible—and no, you don’t need enterprise hardware.

dfranke

jzlegion

ai engineering is just tweaking config values in a notebook until you run out of runpod credits

Pauline_Cx

I'm proud to be part of the GPU Elite, awarded by @runpod_io 😍

Dwayne

Just discovered @runpod_io 🤯🤯🤯 Per second billing for serverless GPU capacity?! Infinitely scalable?! Whaaaat

SuperHumanEpoch

Dean Jones

Runpod has great prices as well

casper_hansen_

Why is Huggingface not adding RunPod as a serverless provider? RunPod is 10-15x cheaper for serverless deployment than AWS and GCP

AlicanKiraz0

Runpod > Sagemaker, VertexAi, AzureML

SaaS Wiz

I love runpod

qtnx_

1.3k spent on the training run, this latest release would not have been possible without runpod

skypilot_org

DataEatsWorld

Thanks @runpod_io, loving all of the updates! 👀

berliangor

i'm a big fan of @runpod_io they're most reliable GPU provider for training and running your models at scale

Mascobot

rachel

thank u runpod i was doing a training run for work when GCP and cloudflare died 🙏🙏 i appreciate u staying online it finished successfully

Yoeven

The @runpod_io event was amazing! One reason we can boast about fast speeds at @jigsawstack is because the cold boot on runpod GPUs is basically nonexistent!

othocs

@runpod_io is so goated, first time trying it today and it’s super easy to setup + their ai helper on discord was very helpful If you ever need cpus/gpus I recommend it!

SkotiVi

oliviawells

Needed a GPU for a quick job, didn’t want to commit to anything long-term. RunPod was perfect for that. Love that I can just spin one up and shut it down after.

YuvrajS9886

winglian

Axolotl works out of the box with @runpod_io's Instant Clusters. It's as easy as running this on each node using the Docker images that we ship.

Dwayne

Just discovered @runpod_io 🤯🤯🤯 Per second billing for serverless GPU capacity?! Infinitely scalable?! Whaaaat

berliangor

i'm a big fan of @runpod_io they're most reliable GPU provider for training and running your models at scale

qtnx_

1.3k spent on the training run, this latest release would not have been possible without runpod

Yoeven

The @runpod_io event was amazing! One reason we can boast about fast speeds at @jigsawstack is because the cold boot on runpod GPUs is basically nonexistent!

Mascobot

jzlegion

ai engineering is just tweaking config values in a notebook until you run out of runpod credits

Dean Jones

Runpod has great prices as well

AlicanKiraz0

Runpod > Sagemaker, VertexAi, AzureML

YuvrajS9886

winglian

Axolotl works out of the box with @runpod_io's Instant Clusters. It's as easy as running this on each node using the Docker images that we ship.

skypilot_org

DrRogerThomp

Trained a 7B parameter model in just 90 minutes for $0.80 using LoRA + Runpod. Yes, it’s possible—and no, you don’t need enterprise hardware.

SuperHumanEpoch

dfranke

othocs

@runpod_io is so goated, first time trying it today and it’s super easy to setup + their ai helper on discord was very helpful If you ever need cpus/gpus I recommend it!

abacaj

Runpod support > lambdalabs support. For on demand GPUs runpod still works the best ime

DataEatsWorld

Thanks @runpod_io, loving all of the updates! 👀

SaaS Wiz

I love runpod

SkotiVi

oliviawells

Needed a GPU for a quick job, didn’t want to commit to anything long-term. RunPod was perfect for that. Love that I can just spin one up and shut it down after.

rachel

thank u runpod i was doing a training run for work when GCP and cloudflare died 🙏🙏 i appreciate u staying online it finished successfully

Pauline_Cx

I'm proud to be part of the GPU Elite, awarded by @runpod_io 😍

casper_hansen_

Why is Huggingface not adding RunPod as a serverless provider? RunPod is 10-15x cheaper for serverless deployment than AWS and GCP

FAQs

Questions? Answers.

Runpod Hub explained.

Runpod Hub is a centralized catalog of preconfigured AI repositories that you can browse, deploy, and share. All repos are optimized for Runpod’s Serverless infrastructure, so you can go from discovery to a running endpoint in minutes.

No—the Hub is currently in beta. We’re actively adding features and fixing bugs. Join our Discord if you’d like to give feedback or report issues.

One-click deployment: All Hub repos come with prebuilt Docker images and Serverless handlers. You don’t have to write Dockerfiles or manage dependencies.

Configuration UI: We expose common parameters (environment variables, model paths, precision settings, etc.) so you can tweak a repo without touching code.

Built-in testing: Every repo in the Hub has automated build-and-test pipelines. You can trust that the code runs properly on Runpod before you click “Deploy.”

Save time: Instead of cloning a repo, installing dependencies, and debugging runtime issues, you can launch a vetted endpoint in minutes.

End users/Developers: Quickly find and run popular AI models (LLMs, Stable Diffusion, OCR, etc.) without setup headaches. Customize inputs via a simple form instead of editing code.

Hub creators: Showcase your open-source work to the Runpod community. Every new GitHub release triggers an automated build/test cycle in our pipeline, ensuring your repo stays up to date.

Enterprises/Teams: Adopt standardized, production-ready AI endpoints without reinventing infrastructure. Onboard developers faster by pointing them to Hub listings rather than internal deployment docs.

In the Runpod console, go to the Hub page.

Browse or search for a repo that matches your needs.

Click on the repo to view details—check hardware requirements (CPU vs. GPU, disk size) and any exposed configuration options.

Click Deploy (or choose an older version via the dropdown).

Click Create Endpoint. Within minutes, you’ll have a live Serverless endpoint you can call via API.

For a more details, check out the docs: https://docs.runpod.io/hub/overview

Prepare a working Serverless implementation in your GitHub repo. You’ll need a handler.py (or equivalent), a Dockerfile, and a README.md.

Add a .runpod/hub.json file with metadata (title, description, category, hardware settings, environment variables, presets).

Add a .runpod/tests.json file that defines one or more test cases to exercise your endpoint (each test should return HTTP 200).

Create a GitHub Release (the Hub indexes releases rather than commits).

In the RunPod console, go to the Hub and click Get Started under “Add your repo.” Enter your GitHub URL and follow the prompts.

Once submitted, our build pipeline will automatically scan, build, and test your repo. After it passes, our team will manually review it. If approved, your repo appears live in the Hub.

For a more details, check out the docs: https://docs.runpod.io/hub/publishing-guide.

Clients