AWS Amazon EC2
g4ad.8xlarge
⚡ 2x GPU • 16 GBPart of the G4AD Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.
Name:
gGPU Graphics & ML Inferenceg = GPU Graphics & ML InferencePowered by GPUs (NVIDIA/AMD) for graphics-intensive applications, video encoding, remote workstations, and machine learning inference.44th Generation4 = 4th GenerationAWS 4th generation hardware platform with updated CPU/system architecture.aAMD EPYCa = AMD EPYCAMD EPYC 7R32 (x86_64). Powered by AMD EPYC x86_64 processors, delivering high core counts and cost-effective compute performance.dDirect-Attached NVMe SSDd = Direct-Attached NVMe SSDEquipped with physical high-speed NVMe SSD instance store volumes attached locally to the host server for temporary scratch and caching.8xlarge8 Extra Large8xlarge = 8 Extra Large32 vCPUs • 128 GB RAM • 1200 GB NVMe SSD • 15 Gbps Network • 2x GPU (16.0 GB VRAM)On-demand, Linux
$1.7340/ hr
~$1,265.82/mo · lowest in US East (N. Virginia), us-east-1Per unit
$0.0542/ vCPU-hr
$0.0135/GB-hrCompute
32vCPUs
32 threads • x86_64Memory
128GB
4.0 GB / vCPUNetwork
15 Gbps
StandardStorage & EBS
1,200 GB NVMe SSD
1,200 GB NVMe SSDOn Google Cloud
g4ad.8xlarge is an accelerated machine. Those are compared by the accelerator, not by vCPU and memory, so this page doesn't pick a match. Browse Google Cloud machines.
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & Processor
ProcessorAMD EPYC 7R32
Architecturex86_64 (x86_64)
vCPUs / Threads32 vCPUs
Physical Cores—
Clock Speed2.8 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare Metal—
Performance & Benchmarks
CoreMark Score609,911
CoreMark / vCPU19,059.7 / core
FFmpeg Transcoding151 FPS
CoreMark per Dollar351,736 score / $
Cost per vCPU-hr$0.0542
Cost per GB-hr$0.0135
Containers & Kubernetes
EKS Max Pods—
Max ENIs—
IPv4/v6 per ENI—
Total Addressable IPs—
CNI Prefix Delegation—
Networking & Bandwidth
Network Performance15 Gbps
Baseline Bandwidth—
Burst / Peak Bandwidth—
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported
Storage & EBS Optimization
Storage ConfigurationNVMe SSD (1200 GB)
Local NVMe Disk1,200 GB NVMe SSD
EBS Baseline Throughput—
EBS Max Throughput—
EBS Baseline IOPS—
EBS Max / Burst IOPS—
Dedicated EBS Throughput3000 Mbps
GPU & Hardware Acceleration
GPU Model—
Accelerator Count2x GPU(s)
Total GPU Memory16.0 GB
Memory Architecture—
Acceleration Runtimes—
Platform & Architecture Details
Hypervisor / System—
Nitro Enclaves—
Normalization Factor64
Generation StatusCurrent Generation (Recommended)
Rates by region
Live on-demand rates across all global AWS cloud regionsLowest Price Region
$1.7340/ hr
US East (N. Virginia) (us-east-1)Highest Price Region
$2.3400/ hr
Asia Pacific (Tokyo) (ap-northeast-1)Global Fleet Average
$1.9512/ hr
Across all active regionsRegional Coverage
8regions
Available worldwide| Region | On-Demand Price | % vs On-Demand Rate |
|---|---|---|
ap-northeast-1 HighestAsia Pacific (Tokyo) | $2.3400 | |
ca-central-1 Canada (Central) | $1.9360 | |
eu-central-1 EU (Frankfurt) | $2.1680 | |
eu-west-1 EU (Ireland) | $1.9360 | |
eu-west-2 EU (London) | $2.0280 | |
us-east-1 LowestUS East (N. Virginia) | $1.7340 | |
us-east-2 LowestUS East (Ohio) | $1.7340 | |
us-west-2 LowestUS West (Oregon) | $1.7340 |
| Region | On-Demand Price | % vs On-Demand Rate |
|---|---|---|
ap-northeast-1 HighestAsia Pacific (Tokyo) | $3.8120 | |
ca-central-1 Canada (Central) | $3.4080 | |
eu-central-1 EU (Frankfurt) | $3.6400 | |
eu-west-1 EU (Ireland) | $3.4080 | |
eu-west-2 EU (London) | $3.5000 | |
us-east-1 LowestUS East (N. Virginia) | $3.2060 | |
us-east-2 LowestUS East (Ohio) | $3.2060 | |
us-west-2 LowestUS West (Oregon) | $3.2060 |
No regions matched your search filter.