GPU Servers

Ephemeral, Scalable GPU servers
product header icon

Cato’s bare metal GPU servers feature graphics processing units (GPUs) specifically designed to accelerate complex computing tasks such as machine learning, scientific simulations, and virtual reality. They are ideal for workloads requiring massive parallel processing power, reducing processing times from days or weeks to hours or even minutes. These servers are available at considerably lower costs than at the big cloud providers for equivalent performance.


G1.P2XL.2NV8 G1.P2XL.2NV8L G2.P2XXL.2NV16L
Processor: 2 x Intel Xeon E5-2680v4 2 x Intel Xeon 8168 2 x Intel Xeon 8174
vCores: 56 96 96
Processor Speed: 3.3GHz 2.7GHz 3.1GHz
On Demand1: $6.6290 $11.1990 $26.9520
Monthly2: $2,903.50 $4,905.16 $11,804.98
SLA: 99.5% 99.5% 99.5%
Memory: 512GB 512GB 1536GB
Network Speed: 25Gbps 50Gbps 50Gbps
Data Transfer3: $0.0025/GiB $0.0025/GiB $0.0025/GiB
Data Transfer Included: 1TiB/month 1TiB/month 1TiB/month
Local Storage: 1x 1TB SATA SSD 6x 2TB SATA SSD 2x 1TB NVMe, 2x 4TB NVMe
Attached Storage: 2x 2TB NVMe
GPU: 8x Nvidia V100 (16GB) 8x Nvidia V100 (32GB) 16x Nvidia V100 (32GB)
GPU Memory: 128GB 256GB 512GB
Cuda Cores: 40,960 40,960 81,920
Tensor Cores: 5,120 5,120 10,240
Subject to availiability; subject to change;
1prices shown in USD;
2shown with annual prepayment and calculated as a 30 day month;
3for egress/ingress from Pod
Cato Digital

Ready to get started?

View available application or storage servers. Get Started
Cato Digital ™, and © Cato Digital, inc  | Terms | Privacy