Accelerate pricing
Powerful dedicated GPU instances to run the most demanding AI and GPU-intensive workloads.
g3.h100.large
- 8 x NVIDIA H100 80GB NVLink GPU
- Dual AMD 9354, 64 Cores @ 3.25 GHz
- 1536 GB RAM
- 4 x 3.8TB NVME
- 2 x 10 Gbps NIC
g3.a100.large
- 8 x NVIDIA A100 80GB NVLink GPU
- Dual AMD 9354, 64 Cores @ 3.25 GHz
- 1536 GB RAM
- 4 x 3.8TB NVME
- 2 x 10 Gbps NIC
g3.h100.medium
- 4 x NVIDIA H100 80GB NVLink GPU
- Dual AMD 9354, 64 Cores @ 3.25 GHz
- 768 GB RAM
- 2 x 3.8TB NVME
- 2 x 10 Gbps NIC
g3.l40s.large
- 8 x NVIDIA L40s 48GB GPU
- Dual AMD 9354, 64 Cores @ 3.25 GHz
- 1536 GB RAM
- 4 x 3.8TB NVME
- 2 x 10 Gbps NIC
g3.gh200
- 1 x NVIDIA Grace Hopper Superchip GPU
- Dual NVIDIA Grace Hopper Superchip, 72 Cores @ 0 GHz
- 480 GB RAM
- 3.8TB NVME960 GB NVME
- 10 Gbps NIC
g3.h100.small
- 1 x NVIDIA H100 80GB GPU
- AMD 9124, 16 Cores @ 3 GHz
- 192 GB RAM
- 2 x 3.8TB NVME
- 2 x 10 Gbps NIC
Included with all servers
- 24/7 specialized support
- 20 TB free outbound every month
- Free inbound traffic
- Unmetered DDoS protection
- 99,9% uptime SLA
- Bandwidth reporting
- IPMI access
- Dashboard and API
- All platform features
Move to Metal
Get credits to experience the most powerful bare metal platform. Eligible companies get up to $10,000 in credits to run workloads on Latitude.sh Metal.
Looking for different configurations?
Do you have a specific project, need to make changes to a specific configuration, or have different needs? Get in touch to discuss other options.
Ready to get started?
Create an account and start deploying bare metal servers globally.Or, contact us to design a custom solution for your business.