g6e.4xlarge
Amazon EC2 · G6e family
The g6e.4xlarge is a gpu & accelerated Amazon EC2 instance type with 16 vCPUs and 128 GiB of memory, 1 × NVIDIA L40S, running on AMD EPYC 7R13 Processor with 20 Gigabit networking, starting at $3.004 per hour on demand.
- vCPUs
- 16
- memory
- 128 GiB
- gpu
- 1× L40S
- on-demand
- $3.004
- spot
- –
- 1-yr reserved
- $1.893
dedicated
8 GiB per vCPU
48 GiB total
$2,193/mo · us-east-1
not offered
−37% vs on-demand
g6e.4xlarge 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 | $3.004 | $1.893 | $1.298 |
| US East (Ohio)us-east-2cheapestNorth America | $3.004 | $1.893 | $1.298 |
| US West (Oregon)us-west-2cheapestNorth America | $3.004 | $1.893 | $1.298 |
| EU (Spain)eu-south-2Europe | $3.166 | $1.994 | $1.368 |
| EU (Stockholm)eu-north-1Europe | $3.187 | $2.008 | $1.377 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $3.608 | $2.273 | $1.559 |
| Asia Pacific (Mumbai)ap-south-1Asia | $3.608 | $2.273 | $1.559 |
| Middle East (UAE)me-central-1Middle East | $3.685 | $2.322 | $1.592 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $3.694 | $2.327 | $1.596 |
| EU (Frankfurt)eu-central-1Europe | $3.757 | $2.367 | $1.623 |
| Asia Pacific (Osaka)ap-northeast-3Asia | $4.357 | $2.745 | $1.882 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $4.357 | $2.745 | $1.882 |
Specifications
compute
- vCPUs
- 16
- Memory
- 128 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
- 600 GB NVME
- Storage detail
- 1 x 600 GB NVMe SSD
- Network
- 20 Gigabit
- Peak bandwidth
- 20 Gbps
accelerators
- Model
- NVIDIA L40S
- Count
- 1
- Memory (total)
- 48 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6e.4xlarge- Family
- G6e
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 12 (Asia, Europe, Middle East, North America)
- Cheapest region
- US East (N. Virginia) · $3.004/hr
- Dedicated EBS throughput
- 8000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 1.61
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 62%
g6e.4xlarge 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.4xlarge |
|---|---|---|---|---|---|---|
| AWS | g6e.4xlarge | 16 | 128 GiB | 1 × NVIDIA L40S | $3.004 | – |
| Vultr | vcg-a40-24c-120g-48vram24 vCPU (1.5×) · 120 GiB (1.1× less) · NVIDIA A40 | 24 | 120 GiB | 1 × NVIDIA A40 | $1.712 | -43% |
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.4xlarge FAQ
How much does g6e.4xlarge cost?
g6e.4xlarge costs $3.004 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $2,193 per month. Across 12 regions the Linux on-demand price ranges from $3.004 in US East (N. Virginia) to $4.357 in Asia Pacific (Osaka). A 1-yr Reserved commitment brings it to $1.893 per hour. With Windows it costs $3.74 per hour.
How many vCPUs and how much memory does g6e.4xlarge have?
g6e.4xlarge has 16 vCPUs and 128 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.4xlarge have?
g6e.4xlarge has 1 × NVIDIA L40S with 48 GiB of accelerator memory in total.
What are the equivalents of g6e.4xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Vultr, vcg-a40-24c-120g-48vram (24 vCPU, 120 GiB, $1.712/hour in Los Angeles).