g6f.4xlarge
Amazon EC2 · G6f family
The g6f.4xlarge is a gpu & accelerated Amazon EC2 instance type with 16 vCPUs and 64 GiB of memory, 1/2 × NVIDIA L4, running on AMD EPYC 7R13 Processor with up to 25 Gigabit networking, starting at $0.95 per hour on demand.
- vCPUs
- 16
- memory
- 64 GiB
- gpu
- 1/2× L4
- on-demand
- $0.95
- spot
- –
- regions
- 13
dedicated
4 GiB per vCPU
12 GiB total
$694/mo · us-east-1
not offered
across 5 areas
g6f.4xlarge price by region
13 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $0.95 |
| US East (Ohio)us-east-2cheapestNorth America | $0.95 |
| US West (Oregon)us-west-2cheapestNorth America | $0.95 |
| EU (Stockholm)eu-north-1Europe | $1.008 |
| Canada (Central)ca-central-1North America | $1.055 |
| EU (Spain)eu-south-2Europe | $1.069 |
| Asia Pacific (Mumbai)ap-south-1Asia | $1.141 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $1.168 |
| EU (Frankfurt)eu-central-1Europe | $1.188 |
| EU (London)eu-west-2Europe | $1.206 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $1.235 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $1.378 |
| South America (Sao Paulo)sa-east-1South America | $1.615 |
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
- 450 GB NVME
- Storage detail
- 1 x 450 NVMe SSD
- Network
- Up to 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 1/2
- Memory (total)
- 12 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6f.4xlarge- Family
- G6f
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 13 (Asia, Europe, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $0.95/hr
- Dedicated EBS throughput
- 8000 Mbps
- Enhanced networking
- Yes
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- 15-20%
- Spot savings vs on-demand (us-east-1)
- 58%
g6f.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 g6f.4xlarge |
|---|---|---|---|---|---|---|
| AWS | g6f.4xlarge | 16 | 64 GiB | 1/2 × NVIDIA L4 | $0.95 | – |
| Azure | NV12ads v710 v512 vCPU (1.3× less) · AMD Radeon Pro V710 | 12 | 64 GiB | 1/2 × AMD Radeon Pro V710 | $1.00 | +5% |
| Google Cloud | g2-standard-161× GPU | 16 | 64 GiB | 1 × NVIDIA L4 | $1.147 | +21% |
G6f family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly |
|---|---|---|---|---|---|---|
| g6f.large | 2 | 8 GiB | 1/8 × NVIDIA L4 | 100 GB NVME | $0.202 | $147 |
| g6f.xlarge | 4 | 16 GiB | 1/8 × NVIDIA L4 | 100 GB NVME | $0.2375 | $173 |
| g6f.2xlarge | 8 | 32 GiB | 1/4 × NVIDIA L4 | 200 GB NVME | $0.475 | $347 |
| g6f.4xlarge | 16 | 64 GiB | 1/2 × NVIDIA L4 | 450 GB NVME | $0.95 | $694 |
g6f.4xlarge FAQ
How much does g6f.4xlarge cost?
g6f.4xlarge costs $0.95 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $694 per month. Across 13 regions the Linux on-demand price ranges from $0.95 in US East (N. Virginia) to $1.615 in South America (Sao Paulo). With Windows it costs $1.686 per hour.
How many vCPUs and how much memory does g6f.4xlarge have?
g6f.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 G6f family.
What GPU does g6f.4xlarge have?
g6f.4xlarge has 1/2 × NVIDIA L4 with 12 GiB of accelerator memory in total.
What are the equivalents of g6f.4xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, NV12ads v710 v5 (12 vCPU, 64 GiB, $1.00/hour in East US); on Google Cloud, g2-standard-16 (16 vCPU, 64 GiB, $1.147/hour in Iowa).