Run any AI model. On a real Windows GPU.

24 GB and 48 GB VRAM available. ComfyUI, Automatic1111, LM Studio — no Linux, no cloud notebooks.

Supported AI tools

Full Windows admin access means you can install anything. Here are the most popular tools our users run.

ComfyUI

Node-based Stable Diffusion workflows with full GPU acceleration

Automatic1111 (SD WebUI)

The most popular Stable Diffusion interface, pre-configured for NVIDIA

LM Studio

Run large language models locally — Llama, Mistral, Mixtral, and more

Ollama

CLI-based LLM runner. Pull and run models in seconds.

Fooocus

Simplified Stable Diffusion — great for beginners

KoboldCpp

Run GGUF models with GPU offloading for text generation

InvokeAI

Professional Stable Diffusion toolkit with a polished UI

LoRA training

Fine-tune Stable Diffusion models with your own data

Choose the right plan based on what you want to run.

Model	VRAM needed	Starter (12 GB)	Standard (24 GB)	Pro (24 GB)	Power (48 GB)
Stable Diffusion XL	8–12 GB	Yes	Yes	Yes	Yes
Flux.1 (dev/schnell)	12–24 GB	Tight	Yes	Yes	Yes
Llama 3 8B (Q4)	~6 GB	Yes	Yes	Yes	Yes
Llama 3 70B (Q4)	~40 GB	No	No	No	Yes
Mixtral 8x7B (Q4)	~26 GB	No	Tight	Tight	Yes
SDXL LoRA training	16–24 GB	No	Yes	Yes	Yes

No command line required

Most AI tools now have native Windows GUIs. ComfyUI, LM Studio, and Fooocus all run with a simple double-click — no terminal, no conda, no Docker.

Full NVIDIA driver support

CloudRig machines come with NVIDIA drivers pre-installed. CUDA and cuDNN work out of the box. No driver conflicts, no dependency hell.

Use your existing workflow

If you already run AI tools on your Windows PC, CloudRig is identical — just faster. No need to learn Linux, SSH, or Jupyter notebooks.

Standard

GPURTX 3090

VRAM24 GB

~$0.60/hr

Great for Stable Diffusion and smaller LLMs

Pro

GPURTX 4090

VRAM24 GB

~$0.90/hr

Faster inference, same VRAM as Standard

Power

GPURTX A6000

VRAM48 GB

~$1.20/hr

Run 70B+ models and large batch jobs