Compare instance

AWS Amazon EC2

inf2.xlarge

⚡ 1x GPU • 32 GB

Part of the INF2 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:infAWS Inferentia Acceleratorsinf = AWS Inferentia AcceleratorsPurpose-built AWS Inferentia silicon designed for ultra-low latency, high-throughput machine learning inference.22nd Generation2 = 2nd GenerationAWS 2nd generation hardware platform with updated CPU/system architecture.xlargeExtra Large (1x)xlarge = Extra Large (1x)4 vCPUs • 16 GB RAM • EBS only • Up to 15 Gbps Network • 1x GPU (32.0 GB VRAM)
On-demand, Linux
$0.7582/ hr
~$553.49/mo · lowest in US East (N. Virginia), us-east-1
Savings Plan, Linux
$0.40943/ hr
From, with a 3-year Compute Savings Plan, No Upfront: −46% vs on-demand rate (us-east-1)
Per unit
$0.1895/ vCPU-hr
$0.0474/GB-hr
Compute
4vCPUs
2 cores • x86_64
Memory
16GB
4.0 GB / vCPU
Network
Up to 15 Gbps
Baseline: 2.083 Gbps
Storage & EBS
1,250MB/s
Max: 40,000 IOPS

Alternatives to inf2.xlarge

OptionPrice vs inf2.xlargeWhy look at it
g4dn.xlargeCompare →
-31%-$0.232/hr
Linux on-demand, us-east-1		Intel (x86_64), newer generation, same vCPU and RAM
g5.xlargeCompare →
+33%+$0.248/hr
Linux on-demand, us-east-1		Newer generation, same vCPU and RAM
g6.xlargeCompare →
+6%+$0.0466/hr
Linux on-demand, us-east-1		Newer generation, same vCPU and RAM

On Google Cloud

inf2.xlarge is an accelerated machine. Those are compared by the accelerator, not by vCPU and memory, so this page doesn't pick a match. Browse Google Cloud machines.

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads4 vCPUs
Physical Cores2
Clock Speed2.95 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score79,657
CoreMark / vCPU19,914.4 / core
FFmpeg Transcoding34 FPS
CoreMark per Dollar105,061 score / $
Cost per vCPU-hr$0.1895
Cost per GB-hr$0.0474

Containers & Kubernetes

EKS Max Pods58 pods
Max ENIs4
IPv4/v6 per ENI15
Total Addressable IPs60 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network PerformanceUp to 15 Gbps
Baseline Bandwidth2.083 Gbps
Burst / Peak Bandwidth15 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only
Local NVMe DiskNone (EBS only)
EBS Baseline Throughput156.25 MB/s
EBS Max Throughput1250 MB/s
EBS Baseline IOPS6,000
EBS Max / Burst IOPS40,000
Dedicated EBS ThroughputUp to 10 Gbps

GPU & Hardware Acceleration

GPU Model—
Accelerator Count1x GPU(s)
Total GPU Memory32.0 GB
Memory Architecture—
Acceleration Runtimes—

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor1
Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$0.7582/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$1.2889/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$0.9830/ hr
Across all active regions
Regional Coverage
14regions
Available worldwide
Linux — Available in all 14 regions
RegionOn-Demand Price
ap-south-1
Asia Pacific (Mumbai)
$0.9857
ap-northeast-2
Asia Pacific (Seoul)
$0.9098
ap-southeast-1
Asia Pacific (Singapore)
$1.0615
ap-southeast-2
Asia Pacific (Sydney)
$0.9857
ap-northeast-1
Asia Pacific (Tokyo)
$1.1373
eu-central-1
EU (Frankfurt)
$1.1373
eu-west-1
EU (Ireland)
$0.9477
eu-west-2
EU (London)
$1.1373
eu-west-3
EU (Paris)
$1.0615
eu-north-1
EU (Stockholm)
$0.8340
sa-east-1
South America (Sao Paulo)
Highest
$1.2889
us-east-1
US East (N. Virginia)
Lowest
$0.7582
us-east-2
US East (Ohio)
Lowest
$0.7582
us-west-2
US West (Oregon)
Lowest
$0.7582