Products

Cloud servers

Cloud servers with per-second billing. Isolated resources will give maximum performance for your project.

GPU servers

Cloud servers with modern RTX and Tesla graphics accelerators for games, rendering, streaming, working with 3D graphics, and artificial intelligence.

Tesla H100

RTX 4090

RTX 3090

RTX 3080

Tesla A100

RTX A5000

Tesla A10

RTX 2080 Ti

Tesla A2

Tesla T4

Tesla V100

All GPU servers

CPU servers

The cloud servers with high-performance Intel Xeon Gold 2nd and 3rd generation CPU are available for 100% of the processor time.
SSD servers NVMe servers
All CPU servers

Dedicated servers

Rent a physically dedicated server for a long term with a monthly payment. Configure it using modern components: Intel Xeon Gold 2nd and 3rd generation processors, up to 10 of the latest RTX and Tesla video accelerators, and up to 8192 GB of RAM per server, SSD and NVMe disks for data centers.

Select a dedicated server

Marketplace

Use popular and modern applications as effective tools for organizing your project. Save time with pre-configured images that already have all the necessary components installed.

Forget about manually downloading and installing the software — just deploy a virtual server with a ready-made image.
Neural networks 3D CUDA Docker / NGC For games Windows images Linux images
All pre-installed images
Features
Prices
FAQ
Contact
Login

ChatWithRTX

System:	Windows Server 2022
Edition:	0.2
Language:	ru

Launch

Achieve new possibilities of Large Language Models with neural net NVIDIA ChatWithRTX

Description

Windows Server 2022 image with preinstalled NVIDIA ChatWithRTX including neural net Llama and Mistral models. Also bundled with Nvidia Driver 551.29.

Category:
Base Windows / Neural Networks

Size:
95.00 GB

Image added:
17.03.2024

Image updated:
19.03.2024

Uses:
8

Avg boot time:
01:38 — 10:12

Getting started

Launch neural network ChatWithRTX shortcut on desktop of your cloud server.

Please note: Loading large models may take time when using HDD volumes. We recommend using Local and Volume-backed SSD cloud servers for fast model loading.