g6.8xlarge
Amazon EC2 · G6 family
The g6.8xlarge is a gpu & accelerated Amazon EC2 instance type with 32 vCPUs and 128 GiB of memory, 1 × NVIDIA L4, running on AMD EPYC 7R13 Processor with 25 Gigabit networking, starting at $2.014 per hour on demand.
- vCPUs
- 32
- memory
- 128 GiB
- gpu
- 1× L4
- on-demand
- $2.014
- spot
- $0.2623
- 1-yr reserved
- $1.311
dedicated
4 GiB per vCPU
24 GiB total
$1,471/mo · us-east-1
−87% vs on-demand
−35% vs on-demand
g6.8xlarge 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 | $2.014 | $0.2623 | $1.311 | $0.9246 |
| US East (Ohio)us-east-2cheapestNorth America | $2.014 | $0.259 | $1.311 | $0.9246 |
| US West (Oregon)us-west-2cheapestNorth America | $2.014 | $0.2597 | $1.311 | $0.9246 |
| EU (Spain)eu-south-2Europe | $2.123 | – | $1.382 | $0.9742 |
| EU (Stockholm)eu-north-1Europe | $2.137 | – | $1.391 | $0.9807 |
| Canada (Central)ca-central-1North America | $2.237 | – | $1.456 | $1.027 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $2.419 | – | $1.575 | $1.11 |
| Asia Pacific (Mumbai)ap-south-1Asia | $2.419 | – | $1.575 | $1.11 |
| Middle East (UAE)me-central-1Middle East | $2.474 | – | $1.61 | $1.135 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $2.477 | – | $1.613 | $1.137 |
| EU (Frankfurt)eu-central-1Europe | $2.519 | – | $1.64 | $1.156 |
| Asia Pacific (Malaysia)ap-southeast-5Asia | $2.538 | – | $1.652 | $1.165 |
| AWS GovCloud (US-East)us-gov-east-1North America | $2.539 | – | – | – |
| AWS GovCloud (US)us-gov-west-1North America | $2.539 | – | $1.653 | $1.165 |
| EU (London)eu-west-2Europe | $2.557 | – | $1.665 | $1.174 |
| EU (Paris)eu-west-3Europe | $2.557 | – | $1.665 | $1.174 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $2.619 | – | $1.705 | $1.202 |
| EU (Zurich)eu-central-2Europe | $2.716 | – | $1.768 | $1.247 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $2.921 | – | $1.902 | $1.341 |
| South America (Sao Paulo)sa-east-1South America | $3.424 | – | $2.229 | $1.572 |
Specifications
compute
- vCPUs
- 32
- Memory
- 128 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
- 900 GB NVME (2 disks)
- Storage detail
- 2 x 450 GB NVMe SSD
- Network
- 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 1
- Memory (total)
- 24 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
aws details
- API name
g6.8xlarge- Family
- G6
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 20 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $2.014/hr
- Dedicated EBS throughput
- 16000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 2.5
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 45%
g6.8xlarge 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 g6.8xlarge |
|---|---|---|---|---|---|---|
| AWS | g6.8xlarge | 32 | 128 GiB | 1 × NVIDIA L4 | $2.014 | – |
| Azure | NV24ads V710 v524 vCPU (1.3× less) · AMD Radeon Pro V710 | 24 | 128 GiB | 1 × AMD Radeon Pro V710 | $2.00 | -1% |
| NG32adms V620 v1176 GiB (1.38×) · AMD Radeon Pro V620 | 32 | 176 GiB | 1 × AMD Radeon Pro V620 | $3.302 | +64% | |
| Google Cloud | g2-standard-32 | 32 | 128 GiB | 1 × NVIDIA L4 | $1.734 | -14% |
| Akamai | RTX4000 Ada x1 X-LargeNVIDIA RTX 4000 Ada | 32 | 128 GiB | 1 × NVIDIA RTX 4000 Ada | $1.53 | -24% |
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
g6.8xlarge FAQ
How much does g6.8xlarge cost?
g6.8xlarge costs $2.014 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $1,471 per month. Across 20 regions the Linux on-demand price ranges from $2.014 in US East (N. Virginia) to $3.424 in South America (Sao Paulo). Spot capacity costs $0.2623 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $1.311 per hour. With Windows it costs $3.486 per hour.
How many vCPUs and how much memory does g6.8xlarge have?
g6.8xlarge has 32 vCPUs and 128 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 g6.8xlarge have?
g6.8xlarge has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.
What are the equivalents of g6.8xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, NV24ads V710 v5 (24 vCPU, 128 GiB, $2.00/hour in East US); 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).