inf1.6xlarge
Amazon EC2 · Inf1 family
The inf1.6xlarge is a gpu & accelerated Amazon EC2 instance type with 24 vCPUs and 48 GiB of memory, 4 × AWS Inferentia, running on Intel Xeon Platinum 8275CL (Cascade Lake) with 25 Gigabit networking, starting at $1.18 per hour on demand.
- vCPUs
- 24
- memory
- 48 GiB
- accelerator
- 4× Inferentia
- on-demand
- $1.18
- spot
- $0.5169
- 1-yr reserved
- $0.744
dedicated
2 GiB per vCPU
32 GiB total
$861/mo · us-east-1
−56% vs on-demand
−37% vs on-demand
inf1.6xlarge price by region
21 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $1.18 | $0.5169 | $0.744 | $0.567 |
| US East (Ohio)us-east-2cheapestNorth America | $1.18 | $0.528 | $0.744 | $0.567 |
| US West (Oregon)us-west-2cheapestNorth America | $1.18 | $0.2671 | $0.744 | $0.567 |
| Asia Pacific (Mumbai)ap-south-1Asia | $1.241 | $0.4009 | $0.782 | $0.597 |
| EU (Stockholm)eu-north-1Europe | $1.254 | $0.1376 | $0.79 | $0.603 |
| Canada (Central)ca-central-1North America | $1.315 | $0.288 | $0.828 | $0.632 |
| EU (Ireland)eu-west-1Europe | $1.315 | $0.5432 | $0.828 | $0.632 |
| EU (Paris)eu-west-3Europe | $1.379 | $0.5773 | $0.869 | $0.663 |
| EU (London)eu-west-2Europe | $1.382 | $0.3838 | $0.871 | $0.664 |
| EU (Milan)eu-south-1Europe | $1.382 | $0.2218 | $0.943 | $0.664 |
| US West (N. California)us-west-1North America | $1.418 | $0.3548 | $0.893 | $0.681 |
| Middle East (Bahrain)me-south-1Middle East | $1.447 | $0.3615 | $0.987 | $0.695 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $1.453 | $0.1789 | $0.915 | $0.698 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $1.475 | $0.4005 | $0.93 | $0.709 |
| EU (Frankfurt)eu-central-1Europe | $1.475 | $0.3975 | $0.93 | $0.709 |
| AWS GovCloud (US-East)us-gov-east-1North America | $1.488 | – | $0.938 | $0.715 |
| AWS GovCloud (US)us-gov-west-1North America | $1.488 | – | $0.938 | $0.715 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $1.594 | $0.3563 | $1.004 | $0.863 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $1.594 | $0.2923 | $1.004 | $0.766 |
| Asia Pacific (Hong Kong)ap-east-1Asia | $1.819 | $0.2019 | $1.146 | $0.874 |
| South America (Sao Paulo)sa-east-1South America | $1.95 | $0.195 | $1.229 | $0.937 |
Specifications
compute
- vCPUs
- 24
- Memory
- 48 GiB
- Memory per vCPU
- 2 GiB
- Processor
- Intel Xeon Platinum 8275CL (Cascade Lake)
- CPU vendor
- Intel
- Architecture
- x86-64
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- AWS Inferentia
- Count
- 4
- Memory (total)
- 32 GiB
- Vendor
- AWS
aws details
- API name
inf1.6xlarge- Family
- Inf1
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 21 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $1.18/hr
- Dedicated EBS throughput
- 3500 Mbps
- Enhanced networking
- No
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 80%
Inf1 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| inf1.xlarge | 4 | 8 GiB | 1 × AWS Inferentia | – | $0.228 | $166 | $0.0908 | $0.144 |
| inf1.2xlarge | 8 | 16 GiB | 1 × AWS Inferentia | – | $0.362 | $264 | $0.1695 | $0.228 |
| inf1.6xlarge | 24 | 48 GiB | 4 × AWS Inferentia | – | $1.18 | $861 | $0.5169 | $0.744 |
| inf1.24xlarge | 96 | 192 GiB | 16 × AWS Inferentia | – | $4.721 | $3,446 | $1.968 | $2.974 |
inf1.6xlarge FAQ
How much does inf1.6xlarge cost?
inf1.6xlarge costs $1.18 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $861 per month. Across 21 regions the Linux on-demand price ranges from $1.18 in US East (N. Virginia) to $1.95 in South America (Sao Paulo). Spot capacity costs $0.5169 per hour (56% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $0.744 per hour.
How many vCPUs and how much memory does inf1.6xlarge have?
inf1.6xlarge has 24 vCPUs and 48 GiB of memory (2 GiB per vCPU), running on Intel Xeon Platinum 8275CL (Cascade Lake). It is a gpu & accelerated instance type in the Inf1 family.
What accelerator does inf1.6xlarge have?
inf1.6xlarge has 4 × AWS Inferentia with 32 GiB of accelerator memory in total.