g6e.12xlarge
Amazon EC2 · G6e family
The g6e.12xlarge is a gpu & accelerated Amazon EC2 instance type with 48 vCPUs and 384 GiB of memory, 4 × NVIDIA L40S, running on AMD EPYC 7R13 Processor with 100 Gigabit networking, starting at $10.49 per hour on demand.
- vCPUs
- 48
- memory
- 384 GiB
- gpu
- 4× L40S
- on-demand
- $10.49
- spot
- –
- 1-yr reserved
- $6.61
dedicated
8 GiB per vCPU
192 GiB total
$7,660/mo · us-east-1
not offered
−37% vs on-demand
g6e.12xlarge price by region
12 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $10.49 | $6.61 | $4.533 |
| US East (Ohio)us-east-2cheapestNorth America | $10.49 | $6.61 | $4.533 |
| US West (Oregon)us-west-2cheapestNorth America | $10.49 | $6.61 | $4.533 |
| EU (Spain)eu-south-2Europe | $11.06 | $6.966 | $4.776 |
| EU (Stockholm)eu-north-1Europe | $11.13 | $7.012 | $4.808 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $12.60 | $7.939 | $5.444 |
| Asia Pacific (Mumbai)ap-south-1Asia | $12.60 | $7.939 | $5.444 |
| Middle East (UAE)me-central-1Middle East | $12.87 | $8.109 | $5.561 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $12.90 | $8.127 | $5.573 |
| EU (Frankfurt)eu-central-1Europe | $13.12 | $8.266 | $5.668 |
| Asia Pacific (Osaka)ap-northeast-3Asia | $15.22 | $9.587 | $6.574 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $15.22 | $9.587 | $6.574 |
Specifications
compute
- vCPUs
- 48
- Memory
- 384 GiB
- Memory per vCPU
- 8 GiB
- Processor
- AMD EPYC 7R13 Processor
- CPU vendor
- AMD
- Architecture
- x86-64
- Clock speed
- 2.6 GHz
- Burstable CPU
- No
storage & network
- Local storage
- 3.8 TB NVME (2 disks)
- Storage detail
- 2 x 1900 GB NVMe SSD
- Network
- 100 Gigabit
- Peak bandwidth
- 100 Gbps
accelerators
- Model
- NVIDIA L40S
- Count
- 4
- Memory (total)
- 192 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6e.12xlarge- Family
- G6e
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 12 (Asia, Europe, Middle East, North America)
- Cheapest region
- US East (N. Virginia) · $10.49/hr
- Dedicated EBS throughput
- 20000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 5.64
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 51%
g6e.12xlarge equivalents on other clouds
closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region
| Provider | Instance | vCPU | Memory | Processor | On-demand | vs g6e.12xlarge |
|---|---|---|---|---|---|---|
| AWS | g6e.12xlarge | 48 | 384 GiB | 4 × NVIDIA L40S | $10.49 | – |
| Google Cloud | a2-highgpu-4g340 GiB (1.1× less) · NVIDIA A100 40GB | 48 | 340 GiB | 4 × NVIDIA A100 40GB | $14.69 | +40% |
G6e family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | 1-yr |
|---|---|---|---|---|---|---|---|
| g6e.xlarge | 4 | 32 GiB | 1 × NVIDIA L40S | 250 GB NVME | $1.861 | $1,359 | $1.172 |
| g6e.2xlarge | 8 | 64 GiB | 1 × NVIDIA L40S | 450 GB NVME | $2.242 | $1,637 | $1.413 |
| g6e.4xlarge | 16 | 128 GiB | 1 × NVIDIA L40S | 600 GB NVME | $3.004 | $2,193 | $1.893 |
| g6e.8xlarge | 32 | 256 GiB | 1 × NVIDIA L40S | 900 GB NVME | $4.529 | $3,306 | $2.853 |
| g6e.12xlarge | 48 | 384 GiB | 4 × NVIDIA L40S | 3.8 TB NVME (2 disks) | $10.49 | $7,660 | $6.61 |
| g6e.16xlarge | 64 | 512 GiB | 1 × NVIDIA L40S | 1.9 TB NVME | $7.577 | $5,531 | $4.774 |
| g6e.24xlarge | 96 | 768 GiB | 4 × NVIDIA L40S | 3.8 TB NVME (2 disks) | $15.07 | $10,998 | $9.491 |
| g6e.48xlarge | 192 | 1,536 GiB | 8 × NVIDIA L40S | 7.6 TB NVME (4 disks) | $30.13 | $21,996 | $18.98 |
g6e.12xlarge FAQ
How much does g6e.12xlarge cost?
g6e.12xlarge costs $10.49 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $7,660 per month. Across 12 regions the Linux on-demand price ranges from $10.49 in US East (N. Virginia) to $15.22 in Asia Pacific (Osaka). A 1-yr Reserved commitment brings it to $6.61 per hour. With Windows it costs $12.70 per hour.
How many vCPUs and how much memory does g6e.12xlarge have?
g6e.12xlarge has 48 vCPUs and 384 GiB of memory (8 GiB per vCPU), running on AMD EPYC 7R13 Processor. It is a gpu & accelerated instance type in the G6e family.
What GPU does g6e.12xlarge have?
g6e.12xlarge has 4 × NVIDIA L40S with 192 GiB of accelerator memory in total.
What are the equivalents of g6e.12xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Google Cloud, a2-highgpu-4g (48 vCPU, 340 GiB, $14.69/hour in Iowa).