Self-Managed Hardware Requirements
LILT can be installed on custom hardware, whether in a private data center or on a variety of cloud platforms. The tables below provide approximate monthly cost estimates for running the base LILT system V3 models in a cloud environment.
Where applicable, long-term pricing discounts for cloud vendors is considered. However, resources (especially storage) may need to be increased to suit your needs. These costs are not a guarantee, rather a reflection of the cloud platform vendor's prices at the time of lookup.
Network, bandwidth, security group, permission management, and other platform costs are not considered in the attached estimate.
Are you interested in installing LILT's self-managed solution? Contact Sales from the LILT homepage!
Last Revised: 24 Feb 2025
AWS Commercial | ||||||||
Platform | Resource Identifier | Specifications | Quantity | Unit | Unit cost [1] | Cost [2] per month | Cost [3] per month | Notes |
AWS | m5.xlarge | 4vCPU / 16G RAM / 200GB | 1 | Hour | $0.192 | $118.93 | $104.33 | K8s Master |
AWS | r5.16xlarge | 64vCPU / 512G RAM / 1TB | 2 | Hour | $8.064 | $4,584.66 | $4,028.40 | K8s Nodes |
AWS | g4ad.8xlarge | 2 GPUs / 32vCPU / 128G RAM / 500GB | 1 | Hour | $1.73 | $1,036.68 | $877.47 | Translate GPU Node |
AWS | g4dn.4xlarge | 1 GPU / 16vCPU / 64G RAM / 500GB | 1 | Hour | $1.20 | $676.56 | $594.07 | Batch GPU Node |
Total Cost | All V3 lang-pairs | $11.18 | $6,416.83 | $5,604.27 | ||||
AWS Top Secret | |||||||
Platform | Resource Identifier | Specifications | Quantity | Unit | Unit cost [1] | Cost [4] per month | Notes |
AWS | m5.xlarge | 4vCPU / 16G RAM / 200GB | 1 | Hour | $0.45 | $226.59 | K8s Master |
AWS | r5.16xlarge | 64vCPU / 512G RAM / 1TB | 2 | Hour | $15.42 | $11,659.52 | K8s Nodes |
AWS | g4dn.12xlarge | 4 GPUs / 48vCPU / 192G RAM / 500GB | 1 | Hour | $11.40 | $8,372.53 | Translate and Batch GPU Node |
Total Cost | All V3 lang-pairs | $27.27 | $20,258.64 | ||||
[1] Price calculated for plan: "On-Demand Instances"
[2] Price calculated for plan: "Compute Savings Plans" (1 year)
[3] Price calculated for plan: "EC2 Instance Savings Plans" (1 year)
[4] Price calculated for plan: "Standard Reserved Instances" (1 year)
Sources:
Commercial: AWS Commercial Estimate using T4 GPUs
Top Secret: AWS Top Secret Estimate using A10G GPUs
Last Revised: 25 Feb 2025
GCP | ||||||||
Platform | Resource Identifier | Specifications | Quantity | Unit | Unit cost [1] | Cost [1] per month | Cost [2] per month | Notes |
GCP | n1-standard-4 | 4vCPU / 15G RAM / 200GB | 1 | Hour | $0.21 | $158.70 | $107.38 | K8s Master |
GCP | n2-highmem-64 | 64vCPU / 512G RAM / 1TB | 2 | Hour | $8.93 | $6,520.97 | $4,255.99 | K8s Nodes |
GCP | n1-highmem-32 | 4 GPUs / 32vCPU / 208G RAM / 1TB | 1 | Hour | $6.86 | $5,007.56 | $3,225.75 | Translate and Batch GPU Node |
Total Cost | All V3 lang-pairs | $16.00 | $11,687.23 | $7,589.12 | ||||
[1] Price calculated for plan: "On-Demand Instances"
[2] Price calculated for plan: "Committed use discount options" (1 year)
Source: GCP Pricing Calculator Estimate
Using T4 GPUs
Last Revised: 25 Feb 2025
Microsoft Azure | ||||||||
|---|---|---|---|---|---|---|---|---|
Platform | Resource Identifier | Specifications | Quantity | Unit | Unit cost [1] | Cost [1] per month | Cost [2] per month | Notes |
Azure | CentOS D3 v2 | 4vCPU / 14G RAM / 256GiB | 1 | Hour | $0.35 | $255.94 | $189.63 | K8s Master |
Azure | CentOS E64as v5 | 64vCPU / 512G RAM / 512GiB | 2 | Hour | $9.50 | $6,936.83 | $5,030.71 | K8s Nodes |
Azure | NC24ads A100 V4 | 1 GPU / 48vCPU / 220G RAM / 512GiB | 2 | Hour | $7.90 | $5,762.77 | $4,864.01 | Translate and Batch GPU Node |
Total Cost | All V3 lang-pairs | $17.75 | $12,955.54 | $10,084.35 | ||||
[1] Price calculated for plan: "Pay as you go"
[2] Price calculated for plan: "1 year savings plan (~31% discount)"
Source: https://azure.microsoft.com/en-us/pricing/calculator/#virtual-machines1
Using A100 GPUs (optionally, 3 T4 GPUs can be used as well, with at least 2 GPUs per node).