Juice Logo

Juice Remote GPU

We’re building software to enable AI and Graphics workloads on remote GPUs.

Our software enables you to offload GPU processing for any CUDA or Vulkan application to a remote host that’s running our agent. We inject our CUDA and Vulkan implementations during runtime, which means you don’t have to make any code changes to your application. We allow a single client to connect to multiple GPUs and multiple clients to share a single GPU.

Use Cases

You can use Juice to share a single GPU across several workstations, allocate GPUs dynamically to CPU-only machines (eg: for serverless functions), and simplify dev workflows and deployments.


Below is a benchmark running SDXL comparing local GPU performance to a remote Juice GPU running on a home network.

We tested Juice Remote GPU with a variety of workloads and found that it performs within 5% of a local GPU when running in the same detacenter.


We currently support the following APIs:

CUDA11.8 - 12.3Windows, Linux
Vulkan1.3Windows, Linux (server-only)
DirectX11, 12Windows, Linux (server-only)
OpenGL4.6Windows, Linux (server-only)

We test our software with the latest versions of PyTorch and TensorFlow . We support AI inference and fine tuning with current LLMs and image diffusion models.

Looking for more information?

We’re happy to help you with any questions you might have. Reach out to us and we’ll get back to you as soon as possible.

About Us

We are a small team of engineers from Meta, Intel, and gaming tech. @deanbeeler was a founding engineer at Oculus and built foundational VR technology like ASW. @stevegolik was an senior executive at Turnitin and Surveymonkey. @yuriykagan led VR system UI engineering at Meta.

@david-mccloskey worked on low level software and hardware for a decade at Intel. @charles-w-baker and @ramon-steenson bring years of experience in gaming, graphics, and data science applications to our team.


KhronosAI Infrastructure Alliance (AIIA)Open Grid Alliance

As Featured In

Wall Street Journal