g6.4xlarge
Amazon EC2 · G6 family
The g6.4xlarge is a gpu & accelerated Amazon EC2 instance type with 16 vCPUs and 64 GiB of memory, 1 × NVIDIA L4, running on AMD EPYC 7R13 Processor with up to 25 Gigabit networking, starting at $1.323 per hour on demand.
- vCPUs
- 16
- memory
- 64 GiB
- gpu
- 1× L4
- on-demand
- $1.323
- spot
- $0.1723
- 1-yr reserved
- $0.8614
dedicated
4 GiB per vCPU
24 GiB total
$966/mo · us-east-1
−87% vs on-demand
−35% vs on-demand
g6.4xlarge price by region
20 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $1.323 | $0.1723 | $0.8614 | $0.6074 |
| US East (Ohio)us-east-2cheapestNorth America | $1.323 | $0.175 | $0.8614 | $0.6074 |
| US West (Oregon)us-west-2cheapestNorth America | $1.323 | $0.1694 | $0.8614 | $0.6074 |
| EU (Spain)eu-south-2Europe | $1.394 | – | $0.9076 | $0.64 |
| EU (Stockholm)eu-north-1Europe | $1.403 | – | $0.9136 | $0.6442 |
| Canada (Central)ca-central-1North America | $1.469 | – | $0.9565 | $0.6744 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $1.589 | – | $1.034 | $0.7293 |
| Asia Pacific (Mumbai)ap-south-1Asia | $1.589 | – | $1.034 | $0.7293 |
| Middle East (UAE)me-central-1Middle East | $1.625 | – | $1.058 | $0.7458 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $1.627 | – | $1.059 | $0.7468 |
| EU (Frankfurt)eu-central-1Europe | $1.655 | – | $1.077 | $0.7595 |
| Asia Pacific (Malaysia)ap-southeast-5Asia | $1.667 | – | $1.085 | $0.7651 |
| AWS GovCloud (US-East)us-gov-east-1North America | $1.668 | – | – | – |
| AWS GovCloud (US)us-gov-west-1North America | $1.668 | – | $1.086 | $0.7655 |
| EU (London)eu-west-2Europe | $1.68 | – | $1.093 | $0.771 |
| EU (Paris)eu-west-3Europe | $1.68 | – | $1.093 | $0.771 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $1.72 | – | $1.12 | $0.7897 |
| EU (Zurich)eu-central-2Europe | $1.784 | – | $1.161 | $0.8188 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $1.919 | – | $1.249 | $0.8808 |
| South America (Sao Paulo)sa-east-1South America | $2.249 | – | $1.464 | $1.032 |
Specifications
compute
- vCPUs
- 16
- Memory
- 64 GiB
- Memory per vCPU
- 4 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
- Up to 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 1
- Memory (total)
- 24 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6.4xlarge- Family
- G6
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 20 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $1.323/hr
- Dedicated EBS throughput
- 8000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 1.64
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 49%
g6.4xlarge 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 g6.4xlarge |
|---|---|---|---|---|---|---|
| AWS | g6.4xlarge | 16 | 64 GiB | 1 × NVIDIA L4 | $1.323 | – |
| Google Cloud | g2-standard-16 | 16 | 64 GiB | 1 × NVIDIA L4 | $1.147 | -13% |
| g2-standard-1212 vCPU (1.3× less) · 48 GiB (1.3× less) | 12 | 48 GiB | 1 × NVIDIA L4 | $1.00 | -24% | |
| Akamai | RTX4000 Ada x1 LargeNVIDIA RTX 4000 Ada | 16 | 64 GiB | 1 × NVIDIA RTX 4000 Ada | $0.96 | -27% |
G6 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| g6.xlarge | 4 | 16 GiB | 1 × NVIDIA L4 | 250 GB NVME | $0.8048 | $588 | $0.105 | $0.5239 |
| g6.2xlarge | 8 | 32 GiB | 1 × NVIDIA L4 | 450 GB NVME | $0.9776 | $714 | $0.1259 | $0.6364 |
| g6.4xlarge | 16 | 64 GiB | 1 × NVIDIA L4 | 600 GB NVME | $1.323 | $966 | $0.1723 | $0.8614 |
| g6.8xlarge | 32 | 128 GiB | 1 × NVIDIA L4 | 900 GB NVME (2 disks) | $2.014 | $1,471 | $0.2623 | $1.311 |
| g6.12xlarge | 48 | 192 GiB | 4 × NVIDIA L4 | 3.8 TB NVME (4 disks) | $4.602 | $3,359 | $0.6045 | $2.996 |
| g6.16xlarge | 64 | 256 GiB | 1 × NVIDIA L4 | 1.9 TB NVME (2 disks) | $3.397 | $2,480 | $0.4404 | $2.211 |
| g6.24xlarge | 96 | 384 GiB | 4 × NVIDIA L4 | 3.8 TB NVME (4 disks) | $6.675 | $4,873 | $0.8597 | $4.346 |
| g6.48xlarge | 192 | 768 GiB | 8 × NVIDIA L4 | 7.5 TB NVME (8 disks) | $13.35 | $9,746 | $1.76 | $8.691 |
Similar instance types on AWS
other AWS families with a similar shape, cheapest first
g6.4xlarge FAQ
How much does g6.4xlarge cost?
g6.4xlarge costs $1.323 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $966 per month. Across 20 regions the Linux on-demand price ranges from $1.323 in US East (N. Virginia) to $2.249 in South America (Sao Paulo). Spot capacity costs $0.1723 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $0.8614 per hour. With Windows it costs $2.059 per hour.
How many vCPUs and how much memory does g6.4xlarge have?
g6.4xlarge has 16 vCPUs and 64 GiB of memory (4 GiB per vCPU), running on AMD EPYC 7R13 Processor. It is a gpu & accelerated instance type in the G6 family.
What GPU does g6.4xlarge have?
g6.4xlarge has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.
What are the equivalents of g6.4xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Google Cloud, g2-standard-16 (16 vCPU, 64 GiB, $1.147/hour in Iowa); on Akamai, RTX4000 Ada x1 Large (16 vCPU, 64 GiB, $0.96/hour in Newark, NJ).