g7.8xlarge
Amazon EC2 · G7 family
The g7.8xlarge is a gpu & accelerated Amazon EC2 instance type with 32 vCPUs and 128 GiB of memory, 1 × NVIDIA GPU (g7), running on Intel Xeon Scalable (Granite Rapids) with 100 Gigabit networking, starting at $4.086 per hour on demand.
- vCPUs
- 32
- memory
- 128 GiB
- gpu
- 1× GPU (g7)
- on-demand
- $4.086
- spot
- –
- regions
- 10
dedicated
4 GiB per vCPU
32 GiB total
$2,983/mo · us-east-1
not offered
across 5 areas
g7.8xlarge price by region
10 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $4.086 |
| US East (Ohio)us-east-2cheapestNorth America | $4.086 |
| US West (Oregon)us-west-2cheapestNorth America | $4.086 |
| EU (Spain)eu-south-2Europe | $4.291 |
| EU (Stockholm)eu-north-1Europe | $4.334 |
| Asia Pacific (Mumbai)ap-south-1Asia | $4.907 |
| EU (Frankfurt)eu-central-1Europe | $5.11 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $5.313 |
| EU (London)eu-west-2Europe | $6.198 |
| South America (Sao Paulo)sa-east-1South America | $8.172 |
Specifications
compute
- vCPUs
- 32
- Memory
- 128 GiB
- Memory per vCPU
- 4 GiB
- Processor
- Intel Xeon Scalable (Granite Rapids)
- CPU vendor
- Intel
- Architecture
- x86-64
- Clock speed
- 3.9 GHz
- Burstable CPU
- No
storage & network
- Local storage
- 930 GB NVME
- Storage detail
- 1x930 GB NVMe SSD
- Network
- 100 Gigabit
- Peak bandwidth
- 100 Gbps
accelerators
- Model
- NVIDIA GPU (g7)
- Count
- 1
- Memory (total)
- 32 GiB
aws details
- API name
g7.8xlarge- Family
- G7
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 10 (Asia, Europe, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $4.086/hr
- Dedicated EBS throughput
- 16000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 1.62
- Processor features
- Intel AMX; Intel AVX; Intel AVX2; Intel AVX512; Intel Turbo
g7.8xlarge 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 g7.8xlarge |
|---|---|---|---|---|---|---|
| AWS | g7.8xlarge | 32 | 128 GiB | 1 × NVIDIA GPU (g7) | $4.086 | – |
| Azure | NG32adms V620 v1176 GiB (1.38×) · AMD Radeon Pro V620 | 32 | 176 GiB | 1 × AMD Radeon Pro V620 | $3.302 | -19% |
| NV24ads V710 v524 vCPU (1.3× less) · AMD Radeon Pro V710 | 24 | 128 GiB | 1 × AMD Radeon Pro V710 | $2.00 | -51% | |
| Google Cloud | g2-standard-32NVIDIA L4 | 32 | 128 GiB | 1 × NVIDIA L4 | $1.734 | -58% |
| Akamai | RTX4000 Ada x1 X-LargeNVIDIA RTX 4000 Ada | 32 | 128 GiB | 1 × NVIDIA RTX 4000 Ada | $1.53 | -63% |
G7 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly |
|---|---|---|---|---|---|---|
| g7.2xlarge | 8 | 32 GiB | 1 × NVIDIA GPU (g7) | 440 GB NVME | $2.52 | $1,840 |
| g7.4xlarge | 16 | 64 GiB | 1 × NVIDIA GPU (g7) | 875 GB NVME | $3.042 | $2,221 |
| g7.8xlarge | 32 | 128 GiB | 1 × NVIDIA GPU (g7) | 930 GB NVME | $4.086 | $2,983 |
| g7.12xlarge | 48 | 192 GiB | 2 × NVIDIA GPU (g7) | 1.9 TB NVME | $7.128 | $5,204 |
| g7.24xlarge | 96 | 384 GiB | 4 × NVIDIA GPU (g7) | 3.8 TB NVME | $14.26 | $10,407 |
| g7.48xlarge | 192 | 768 GiB | 8 × NVIDIA GPU (g7) | 7.6 TB NVME (2 disks) | $28.51 | $20,815 |
g7.8xlarge FAQ
How much does g7.8xlarge cost?
g7.8xlarge costs $4.086 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $2,983 per month. Across 10 regions the Linux on-demand price ranges from $4.086 in US East (N. Virginia) to $8.172 in South America (Sao Paulo). With Windows it costs $5.558 per hour.
How many vCPUs and how much memory does g7.8xlarge have?
g7.8xlarge has 32 vCPUs and 128 GiB of memory (4 GiB per vCPU), running on Intel Xeon Scalable (Granite Rapids). It is a gpu & accelerated instance type in the G7 family.
What GPU does g7.8xlarge have?
g7.8xlarge has 1 × NVIDIA GPU (g7) with 32 GiB of accelerator memory in total.
What are the equivalents of g7.8xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, NG32adms V620 v1 (32 vCPU, 176 GiB, $3.302/hour in East US 2); on Google Cloud, g2-standard-32 (32 vCPU, 128 GiB, $1.734/hour in Iowa); on Akamai, RTX4000 Ada x1 X-Large (32 vCPU, 128 GiB, $1.53/hour in Newark, NJ).