g6.12xlarge
Amazon EC2 · G6 family
The g6.12xlarge is a gpu & accelerated Amazon EC2 instance type with 48 vCPUs and 192 GiB of memory, 4 × NVIDIA L4, running on AMD EPYC 7R13 Processor with 40 Gigabit networking, starting at $4.602 per hour on demand.
- vCPUs
- 48
- memory
- 192 GiB
- gpu
- 4× L4
- on-demand
- $4.602
- spot
- $0.6045
- 1-yr reserved
- $2.996
dedicated
4 GiB per vCPU
96 GiB total
$3,359/mo · us-east-1
−87% vs on-demand
−35% vs on-demand
g6.12xlarge 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 | $4.602 | $0.6045 | $2.996 | $2.112 |
| US East (Ohio)us-east-2cheapestNorth America | $4.602 | $0.584 | $2.996 | $2.112 |
| US West (Oregon)us-west-2cheapestNorth America | $4.602 | $0.5961 | $2.996 | $2.112 |
| EU (Spain)eu-south-2Europe | $4.849 | – | $3.156 | $2.226 |
| EU (Stockholm)eu-north-1Europe | $4.881 | – | $3.177 | $2.24 |
| Canada (Central)ca-central-1North America | $5.109 | – | $3.326 | $2.345 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $5.526 | – | $3.597 | $2.536 |
| Asia Pacific (Mumbai)ap-south-1Asia | $5.526 | – | $3.597 | $2.536 |
| Middle East (UAE)me-central-1Middle East | $5.65 | – | $3.678 | $2.594 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $5.658 | – | $3.684 | $2.597 |
| EU (Frankfurt)eu-central-1Europe | $5.754 | – | $3.746 | $2.641 |
| Asia Pacific (Malaysia)ap-southeast-5Asia | $5.797 | – | $3.774 | $2.661 |
| AWS GovCloud (US-East)us-gov-east-1North America | $5.80 | – | – | – |
| AWS GovCloud (US)us-gov-west-1North America | $5.80 | – | $3.776 | $2.662 |
| EU (London)eu-west-2Europe | $5.841 | – | $3.803 | $2.681 |
| EU (Paris)eu-west-3Europe | $5.841 | – | $3.803 | $2.681 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $5.983 | – | $3.895 | $2.746 |
| EU (Zurich)eu-central-2Europe | $6.204 | – | $4.039 | $2.848 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $6.674 | – | $4.345 | $3.063 |
| South America (Sao Paulo)sa-east-1South America | $7.822 | – | $5.092 | $3.59 |
Specifications
compute
- vCPUs
- 48
- Memory
- 192 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
- 3.8 TB NVME (4 disks)
- Storage detail
- 4 X 940 GB NVMe SSD
- Network
- 40 Gigabit
- Peak bandwidth
- 40 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 4
- Memory (total)
- 96 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6.12xlarge- Family
- G6
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 20 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $4.602/hr
- Dedicated EBS throughput
- 20000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 5.72
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- 5-10%
- Spot savings vs on-demand (us-east-1)
- 51%
g6.12xlarge 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 g6.12xlarge |
|---|---|---|---|---|---|---|
| AWS | g6.12xlarge | 48 | 192 GiB | 4 × NVIDIA L4 | $4.602 | – |
| Google Cloud | g2-standard-48 | 48 | 192 GiB | 4 × NVIDIA L4 | $4.002 | -13% |
| Akamai | RTX4000 Ada x4 MediumNVIDIA RTX 4000 Ada | 48 | 196 GiB | 4 × NVIDIA RTX 4000 Ada | $3.57 | -22% |
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
g6.12xlarge FAQ
How much does g6.12xlarge cost?
g6.12xlarge costs $4.602 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $3,359 per month. Across 20 regions the Linux on-demand price ranges from $4.602 in US East (N. Virginia) to $7.822 in South America (Sao Paulo). Spot capacity costs $0.6045 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $2.996 per hour. With Windows it costs $6.81 per hour.
How many vCPUs and how much memory does g6.12xlarge have?
g6.12xlarge has 48 vCPUs and 192 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 g6.12xlarge have?
g6.12xlarge has 4 × NVIDIA L4 with 96 GiB of accelerator memory in total.
What are the equivalents of g6.12xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Google Cloud, g2-standard-48 (48 vCPU, 192 GiB, $4.002/hour in Iowa); on Akamai, RTX4000 Ada x4 Medium (48 vCPU, 196 GiB, $3.57/hour in Newark, NJ).