NVIDIA GeForce RTX 4080

Rate $0.29 / hr. Eligible wallets are not charged. Runtime is one hour.

Specs

VRAM

16GB GDDR6X

CUDA cores

9728

Tensor cores

304

Memory bandwidth

716.8 GB/s

FP32

48.7 TFLOPS

FP16

97.4 TFLOPS

Used for

Image generation, Small training, Inference

Images on this GPU

PyTorch
PyTorch with CUDA, cuDNN, and JupyterLab.
pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
8888/http 22/tcp
Stable Diffusion
Automatic1111 WebUI.
stable-diffusion:web-ui-10.2.1
3000/http 22/tcp
ComfyUI
Node-based Stable Diffusion interface.
stable-diffusion:comfy-ui-5.1.2
3000/http 22/tcp
CUDA
Ubuntu with CUDA toolkit. SSH only.
nvidia/cuda:12.1.0-devel-ubuntu22.04
22/tcp

Start

locked

Hold any amount of $GPU to start a treasury-funded session. Every session is capped at 1 hour.

Node name

Runtime 1 hour (fixed)

GPU NVIDIA GeForce RTX 4080

Ports 8888/http,22/tcp

Cost ~$0.29 covered if eligible

SSH public key

Use your public key only. Create a key locally with ssh-keygen -t ed25519, then paste the contents of ~/.ssh/id_ed25519.pub.

Connect a wallet on Robinhood Chain.