Find GPUsL40

Configure your instance

Choose the resources and software for your workload.

Ada Lovelace

1 Configuration
2 Your account
3 Deploy

Compute

L40 · 48 GB GDDR6 per GPU

GPUs per node

1 × L4012 vCPU · 96 GB RAM1,000 GB local NVMe2 × L4024 vCPU · 192 GB RAM2,000 GB local NVMe4 × L4048 vCPU · 384 GB RAM4,000 GB local NVMe8 × L4096 vCPU · 768 GB RAM8,000 GB local NVMe

Pricing plan

Spot $0.090/ GPU-hourLower price. A 2-minute notice before interruption.On-demand $0.190/ GPU-hourContinuous capacity for uninterrupted workloads.

Region

Keep your compute close to your data.

US EastVirginia · 100 Gbps16 GPUs availableEU CentralFrankfurt · 100 Gbps16 GPUs available

Software template

Choose the tools for your workload.

Environment

vLLM with OpenAI-compatible server on port 8000, Hugging Face cache on the persistent disk.

Explore all 9 templates

Storage & identity

Local NVMe is included. Add persistent storage for data you want to keep.

Persistent disk (GB)Instance name Optional

Persistent storage: $0.08/GB-month, including while the instance is stopped. Set to 0 to use only the included local disk.

Whole node / hour$0.090