g5g.16xlarge
Amazon EC2 · G5g family
The g5g.16xlarge is a gpu & accelerated Amazon EC2 instance type with 64 vCPUs and 128 GiB of memory, 2 × NVIDIA T4G, running on AWS Graviton2 Processor with 25 Gigabit networking, starting at $2.744 per hour on demand.
- vCPUs
- 64
- memory
- 128 GiB
- gpu
- 2× T4G
- on-demand
- $2.744
- spot
- $1.19
- 1-yr reserved
- $1.729
dedicated
2 GiB per vCPU
32 GiB total
$2,003/mo · us-east-1
−57% vs on-demand
−37% vs on-demand
g5g.16xlarge price by region
7 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $2.744 | $1.19 | $1.729 | $1.185 |
| US West (Oregon)us-west-2cheapestNorth America | $2.744 | $0.2858 | $1.729 | $1.185 |
| EU (Spain)eu-south-2Europe | $3.062 | $1.041 | $2.089 | $1.321 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $3.375 | $0.3375 | $2.122 | $1.456 |
| EU (Frankfurt)eu-central-1Europe | $3.433 | $0.604 | $2.341 | $1.67 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $3.704 | $0.3704 | $2.528 | $1.884 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $3.84 | $0.384 | $2.419 | $1.868 |
Specifications
compute
- vCPUs
- 64
- Memory
- 128 GiB
- Memory per vCPU
- 2 GiB
- Processor
- AWS Graviton2 Processor
- CPU vendor
- AWS Graviton
- Architecture
- Arm64
- Clock speed
- 2.5 GHz
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- NVIDIA T4G
- Count
- 2
- Memory (total)
- 32 GiB
- Architecture
- Turing
- Vendor
- NVIDIA
aws details
- API name
g5g.16xlarge- Family
- G5g
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 7 (Asia, Europe, North America)
- Cheapest region
- US East (N. Virginia) · $2.744/hr
- Dedicated EBS throughput
- 19000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 6.53
- Spot interruption rate (us-east-1)
- 10-15%
- Spot savings vs on-demand (us-east-1)
- 78%
G5g family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| g5g.xlarge | 4 | 8 GiB | 1 × NVIDIA T4G | – | $0.42 | $307 | $0.1822 | $0.2646 |
| g5g.2xlarge | 8 | 16 GiB | 1 × NVIDIA T4G | – | $0.556 | $406 | $0.2495 | $0.3503 |
| g5g.4xlarge | 16 | 32 GiB | 1 × NVIDIA T4G | – | $0.828 | $604 | $0.3538 | $0.5216 |
| g5g.8xlarge | 32 | 64 GiB | 1 × NVIDIA T4G | – | $1.372 | $1,002 | $0.5815 | $0.8644 |
| g5g.16xlarge | 64 | 128 GiB | 2 × NVIDIA T4G | – | $2.744 | $2,003 | $1.19 | $1.729 |
| g5g.metal | 64 | 128 GiB | 2 × NVIDIA T4G | – | $2.744 | $2,003 | $1.183 | $1.729 |
g5g.16xlarge FAQ
How much does g5g.16xlarge cost?
g5g.16xlarge costs $2.744 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $2,003 per month. Across 7 regions the Linux on-demand price ranges from $2.744 in US East (N. Virginia) to $3.84 in Asia Pacific (Singapore). Spot capacity costs $1.19 per hour (57% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $1.729 per hour.
How many vCPUs and how much memory does g5g.16xlarge have?
g5g.16xlarge has 64 vCPUs and 128 GiB of memory (2 GiB per vCPU), running on AWS Graviton2 Processor. It is a gpu & accelerated instance type in the G5g family.
What GPU does g5g.16xlarge have?
g5g.16xlarge has 2 × NVIDIA T4G with 32 GiB of accelerator memory in total.