inf2.xlarge
Amazon EC2 · Inf2 family
The inf2.xlarge is a gpu & accelerated Amazon EC2 instance type with 4 vCPUs and 16 GiB of memory, 1 × AWS Inferentia2, running on AMD EPYC 7R13 Processor with up to 15 Gigabit networking, starting at $0.7582 per hour on demand.
- vCPUs
- 4
- memory
- 16 GiB
- accelerator
- 1× Inferentia2
- on-demand
- $0.7582
- spot
- $0.3178
- 1-yr reserved
- $0.4777
dedicated
4 GiB per vCPU
32 GiB total
$553/mo · us-east-1
−58% vs on-demand
−37% vs on-demand
inf2.xlarge price by region
14 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $0.7582 | $0.3178 | $0.4777 | $0.3275 |
| US East (Ohio)us-east-2cheapestNorth America | $0.7582 | $0.1203 | $0.4777 | $0.3275 |
| US West (Oregon)us-west-2cheapestNorth America | $0.7582 | $0.1028 | $0.4777 | $0.3275 |
| EU (Stockholm)eu-north-1Europe | $0.834 | $0.0834 | $0.5254 | $0.3603 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $0.9098 | – | – | – |
| EU (Ireland)eu-west-1Europe | $0.9478 | $0.3008 | $0.5971 | $0.4094 |
| Asia Pacific (Mumbai)ap-south-1Asia | $0.9857 | $0.2981 | $0.621 | $0.4586 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $0.9857 | $0.1004 | $0.621 | $0.4258 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $1.061 | $0.1096 | $0.6687 | $0.4586 |
| EU (Paris)eu-west-3Europe | $1.061 | $0.1081 | $0.6687 | $0.4913 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $1.137 | $0.2619 | $0.7165 | $0.5241 |
| EU (Frankfurt)eu-central-1Europe | $1.137 | $0.1344 | $0.7165 | $0.5241 |
| EU (London)eu-west-2Europe | $1.137 | $0.1407 | $0.7165 | $0.5241 |
| South America (Sao Paulo)sa-east-1South America | $1.289 | $0.1289 | $0.812 | $0.5568 |
Specifications
compute
- vCPUs
- 4
- Memory
- 16 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 15 Gigabit
- Peak bandwidth
- 15 Gbps
accelerators
- Model
- AWS Inferentia2
- Count
- 1
- Memory (total)
- 32 GiB
- Vendor
- AWS
aws details
- API name
inf2.xlarge- Family
- Inf2
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 14 (Asia, Europe, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $0.7582/hr
- Dedicated EBS throughput
- Up to 10 Gbps
- Enhanced networking
- Yes
- Normalization size factor
- 1
- Processor features
- AMD Turbo; AVX; AVX2
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 84%
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.xlarge FAQ
How much does inf2.xlarge cost?
inf2.xlarge costs $0.7582 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $553 per month. Across 14 regions the Linux on-demand price ranges from $0.7582 in US East (N. Virginia) to $1.289 in South America (Sao Paulo). Spot capacity costs $0.3178 per hour (58% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $0.4777 per hour.
How many vCPUs and how much memory does inf2.xlarge have?
inf2.xlarge has 4 vCPUs and 16 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.xlarge have?
inf2.xlarge has 1 × AWS Inferentia2 with 32 GiB of accelerator memory in total.