g6.2xlarge
Amazon EC2 · G6 family
The g6.2xlarge is a gpu & accelerated Amazon EC2 instance type with 8 vCPUs and 32 GiB of memory, 1 × NVIDIA L4, running on AMD EPYC 7R13 Processor with up to 10 Gigabit networking, starting at $0.9776 per hour on demand.
- vCPUs
- 8
- memory
- 32 GiB
- gpu
- 1× L4
- on-demand
- $0.9776
- spot
- $0.1259
- 1-yr reserved
- $0.6364
dedicated
4 GiB per vCPU
24 GiB total
$714/mo · us-east-1
−87% vs on-demand
−35% vs on-demand
g6.2xlarge 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 | $0.9776 | $0.1259 | $0.6364 | $0.4487 |
| US East (Ohio)us-east-2cheapestNorth America | $0.9776 | $0.1261 | $0.6364 | $0.4487 |
| US West (Oregon)us-west-2cheapestNorth America | $0.9776 | $0.1286 | $0.6364 | $0.4487 |
| EU (Spain)eu-south-2Europe | $1.03 | – | $0.6706 | $0.4728 |
| EU (Stockholm)eu-north-1Europe | $1.037 | – | $0.675 | $0.4759 |
| Canada (Central)ca-central-1North America | $1.085 | – | $0.7066 | $0.4982 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $1.174 | – | $0.7642 | $0.5388 |
| Asia Pacific (Mumbai)ap-south-1Asia | $1.174 | – | $0.7642 | $0.5388 |
| Middle East (UAE)me-central-1Middle East | $1.20 | – | $0.7815 | $0.551 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $1.202 | – | $0.7826 | $0.5518 |
| EU (Frankfurt)eu-central-1Europe | $1.222 | – | $0.7958 | $0.5611 |
| Asia Pacific (Malaysia)ap-southeast-5Asia | $1.231 | – | $0.8017 | $0.5653 |
| AWS GovCloud (US-East)us-gov-east-1North America | $1.232 | – | – | – |
| AWS GovCloud (US)us-gov-west-1North America | $1.232 | – | $0.8022 | $0.5656 |
| EU (London)eu-west-2Europe | $1.241 | – | $0.8079 | $0.5696 |
| EU (Paris)eu-west-3Europe | $1.241 | – | $0.8079 | $0.5696 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $1.271 | – | $0.8275 | $0.5834 |
| EU (Zurich)eu-central-2Europe | $1.318 | – | $0.858 | $0.6049 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $1.418 | – | $0.923 | $0.6508 |
| South America (Sao Paulo)sa-east-1South America | $1.662 | – | $1.082 | $0.7627 |
Specifications
compute
- vCPUs
- 8
- Memory
- 32 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
- 450 GB NVME
- Storage detail
- 1 x 450 GB NVMe SSD
- Network
- Up to 10 Gigabit
- Peak bandwidth
- 10 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 1
- Memory (total)
- 24 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6.2xlarge- Family
- G6
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 20 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $0.9776/hr
- Dedicated EBS throughput
- Up to 5000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 1.21
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- 10-15%
- Spot savings vs on-demand (us-east-1)
- 46%
g6.2xlarge 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 g6.2xlarge |
|---|---|---|---|---|---|---|
| AWS | g6.2xlarge | 8 | 32 GiB | 1 × NVIDIA L4 | $0.9776 | – |
| Google Cloud | g2-standard-8 | 8 | 32 GiB | 1 × NVIDIA L4 | $0.8536 | -13% |
| g2-standard-1212 vCPU (1.5×) · 48 GiB (1.5×) | 12 | 48 GiB | 1 × NVIDIA L4 | $1.00 | +2% | |
| Akamai | Dedicated 32GB + RTX6000 GPU x1NVIDIA Quadro RTX 6000 | 8 | 32 GiB | 1 × NVIDIA Quadro RTX 6000 | $1.50 | +53% |
| RTX4000 Ada x1 MediumNVIDIA RTX 4000 Ada | 8 | 32 GiB | 1 × NVIDIA RTX 4000 Ada | $0.67 | -31% |
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
g6.2xlarge FAQ
How much does g6.2xlarge cost?
g6.2xlarge costs $0.9776 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $714 per month. Across 20 regions the Linux on-demand price ranges from $0.9776 in US East (N. Virginia) to $1.662 in South America (Sao Paulo). Spot capacity costs $0.1259 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $0.6364 per hour. With Windows it costs $1.346 per hour.
How many vCPUs and how much memory does g6.2xlarge have?
g6.2xlarge has 8 vCPUs and 32 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 g6.2xlarge have?
g6.2xlarge has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.
What are the equivalents of g6.2xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Google Cloud, g2-standard-8 (8 vCPU, 32 GiB, $0.8536/hour in Iowa); on Akamai, Dedicated 32GB + RTX6000 GPU x1 (8 vCPU, 32 GiB, $1.50/hour in Newark, NJ).