inf2.8xlarge
Amazon EC2 · Inf2 family
The inf2.8xlarge is a gpu & accelerated Amazon EC2 instance type with 32 vCPUs and 128 GiB of memory, 1 × AWS Inferentia2, running on AMD EPYC 7R13 Processor with up to 25 Gigabit networking, starting at $1.968 per hour on demand.
- vCPUs
- 32
- memory
- 128 GiB
- accelerator
- 1× Inferentia2
- on-demand
- $1.968
- spot
- $0.7988
- 1-yr reserved
- $1.24
dedicated
4 GiB per vCPU
32 GiB total
$1,437/mo · us-east-1
−59% vs on-demand
−37% vs on-demand
inf2.8xlarge 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 | $1.968 | $0.7988 | $1.24 | $0.8501 |
| US East (Ohio)us-east-2cheapestNorth America | $1.968 | $0.5736 | $1.24 | $0.8501 |
| US West (Oregon)us-west-2cheapestNorth America | $1.968 | $0.4702 | $1.24 | $0.8501 |
| EU (Stockholm)eu-north-1Europe | $2.165 | $0.2195 | $1.364 | $0.9351 |
| EU (Ireland)eu-west-1Europe | $2.46 | $0.8553 | $1.55 | $1.063 |
| Asia Pacific (Mumbai)ap-south-1Asia | $2.558 | $0.9077 | $1.612 | $1.19 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $2.558 | $0.2601 | $1.612 | $1.105 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $2.755 | $0.2755 | $1.736 | $1.19 |
| EU (Paris)eu-west-3Europe | $2.755 | $0.2832 | $1.736 | $1.275 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $2.952 | $0.7362 | $1.86 | $1.36 |
| EU (Frankfurt)eu-central-1Europe | $2.952 | $0.7727 | $1.86 | $1.36 |
| EU (London)eu-west-2Europe | $2.952 | $0.3581 | $1.86 | $1.36 |
| South America (Sao Paulo)sa-east-1South America | $3.345 | $0.3345 | $2.108 | $1.445 |
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
- 2.95 GHz
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- Up to 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- AWS Inferentia2
- Count
- 1
- Memory (total)
- 32 GiB
- Vendor
- AWS
aws details
- API name
inf2.8xlarge- Family
- Inf2
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 13 (Asia, Europe, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $1.968/hr
- Dedicated EBS throughput
- 10 Gbps
- Enhanced networking
- Yes
- Normalization size factor
- 2.6
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 73%
Inf2 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| inf2.xlarge | 4 | 16 GiB | 1 × AWS Inferentia2 | – | $0.7582 | $553 | $0.3178 | $0.4777 |
| inf2.8xlarge | 32 | 128 GiB | 1 × AWS Inferentia2 | – | $1.968 | $1,437 | $0.7988 | $1.24 |
| inf2.24xlarge | 96 | 384 GiB | 6 × AWS Inferentia2 | – | $6.491 | $4,738 | $2.445 | $4.089 |
| inf2.48xlarge | 192 | 768 GiB | 12 × AWS Inferentia2 | – | $12.98 | $9,476 | $5.048 | $8.178 |
inf2.8xlarge FAQ
How much does inf2.8xlarge cost?
inf2.8xlarge costs $1.968 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $1,437 per month. Across 13 regions the Linux on-demand price ranges from $1.968 in US East (N. Virginia) to $3.345 in South America (Sao Paulo). Spot capacity costs $0.7988 per hour (59% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $1.24 per hour.
How many vCPUs and how much memory does inf2.8xlarge have?
inf2.8xlarge 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 Inf2 family.
What accelerator does inf2.8xlarge have?
inf2.8xlarge has 1 × AWS Inferentia2 with 32 GiB of accelerator memory in total.