g4ad.2xlarge
Amazon EC2 · G4ad family
The g4ad.2xlarge is a gpu & accelerated Amazon EC2 instance type with 8 vCPUs and 32 GiB of memory, 1 × AMD Radeon Pro V520, running on AMD EPYC 7R32 with up to 10 Gigabit networking, starting at $0.5412 per hour on demand.
- vCPUs
- 8
- memory
- 32 GiB
- gpu
- 1× Radeon Pro V520
- on-demand
- $0.5412
- spot
- $0.2507
- regions
- 8
dedicated
4 GiB per vCPU
8 GiB total
$395/mo · us-east-1
−54% vs on-demand
across 3 areas
g4ad.2xlarge price by region
8 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $0.5412 | $0.2507 |
| US East (Ohio)us-east-2cheapestNorth America | $0.5412 | $0.1669 |
| US West (Oregon)us-west-2cheapestNorth America | $0.5412 | $0.2151 |
| Canada (Central)ca-central-1North America | $0.6042 | $0.1702 |
| EU (Ireland)eu-west-1Europe | $0.6042 | $0.2389 |
| EU (London)eu-west-2Europe | $0.6329 | $0.2305 |
| EU (Frankfurt)eu-central-1Europe | $0.6766 | $0.2087 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $0.7303 | $0.1811 |
Specifications
compute
- vCPUs
- 8
- Memory
- 32 GiB
- Memory per vCPU
- 4 GiB
- Processor
- AMD EPYC 7R32
- CPU vendor
- AMD
- Architecture
- x86-64
- Clock speed
- 2.8 GHz
- Burstable CPU
- No
storage & network
- Local storage
- 300 GB NVME
- Storage detail
- 300 GB NVMe SSD
- Network
- Up to 10 Gigabit
- Peak bandwidth
- 10 Gbps
accelerators
- Model
- AMD Radeon Pro V520
- Count
- 1
- Memory (total)
- 8 GiB
- Architecture
- RDNA
- Vendor
- AMD
aws details
- API name
g4ad.2xlarge- Family
- G4ad
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 8 (Asia, Europe, North America)
- Cheapest region
- US East (N. Virginia) · $0.5412/hr
- Dedicated EBS throughput
- Up to 3000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 19.97
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- <5%
- Spot savings vs on-demand (us-east-1)
- 55%
g4ad.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 g4ad.2xlarge |
|---|---|---|---|---|---|---|
| AWS | g4ad.2xlarge | 8 | 32 GiB | 1 × AMD Radeon Pro V520 | $0.5412 | – |
| Akamai | RTX4000 Ada x1 MediumNVIDIA RTX 4000 Ada | 8 | 32 GiB | 1 × NVIDIA RTX 4000 Ada | $0.67 | +24% |
| Dedicated 32GB + RTX6000 GPU x1NVIDIA Quadro RTX 6000 | 8 | 32 GiB | 1 × NVIDIA Quadro RTX 6000 | $1.50 | +177% |
G4ad family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot |
|---|---|---|---|---|---|---|---|
| g4ad.xlarge | 4 | 16 GiB | 1 × AMD Radeon Pro V520 | 150 GB NVME | $0.3785 | $276 | $0.1652 |
| g4ad.2xlarge | 8 | 32 GiB | 1 × AMD Radeon Pro V520 | 300 GB NVME | $0.5412 | $395 | $0.2507 |
| g4ad.4xlarge | 16 | 64 GiB | 1 × AMD Radeon Pro V520 | 600 GB NVME | $0.867 | $633 | $0.4216 |
| g4ad.8xlarge | 32 | 128 GiB | 2 × AMD Radeon Pro V520 | 1.2 TB NVME | $1.734 | $1,266 | $0.797 |
| g4ad.16xlarge | 64 | 256 GiB | 4 × AMD Radeon Pro V520 | 2.4 TB NVME | $3.468 | $2,532 | $1.429 |
g4ad.2xlarge FAQ
How much does g4ad.2xlarge cost?
g4ad.2xlarge costs $0.5412 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $395 per month. Across 8 regions the Linux on-demand price ranges from $0.5412 in US East (N. Virginia) to $0.7303 in Asia Pacific (Tokyo). Spot capacity costs $0.2507 per hour (54% less), but can be reclaimed. With Windows it costs $0.9092 per hour.
How many vCPUs and how much memory does g4ad.2xlarge have?
g4ad.2xlarge has 8 vCPUs and 32 GiB of memory (4 GiB per vCPU), running on AMD EPYC 7R32. It is a gpu & accelerated instance type in the G4ad family.
What GPU does g4ad.2xlarge have?
g4ad.2xlarge has 1 × AMD Radeon Pro V520 with 8 GiB of accelerator memory in total.
What are the equivalents of g4ad.2xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Akamai, RTX4000 Ada x1 Medium (8 vCPU, 32 GiB, $0.67/hour in Newark, NJ).