General Purpose

  • T3
  • T2
  • M5
  • M5a
  • M4
  • T3a (Coming Soon)
  • T3
  • T3 instances are the next generation burstable general-purpose instance type that provide a baseline level of CPU performance with the ability to burst CPU usage at any time for as long as required. T3 instances offer a balance of compute, memory, and network resources and are designed for applications with moderate CPU usage that experience temporary spikes in use.

    T3 instances accumulate CPU credits when a workload is operating below baseline threshold. Each earned CPU credit provides the T3 instance the opportunity to burst with the performance of a full CPU core for one minute when needed. T3 instances can burst at any time for as long as required in Unlimited mode.

    Features:

    • Burstable CPU, governed by CPU Credits, and consistent baseline performance
    • Unlimited mode by default to ensure performance during peak periods and Standard mode option for a predictable monthly cost
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • AWS Nitro System and high frequency Intel Xeon Scalable processors result in up to a 30% price performance improvement over T2 instances
    Model vCPU* CPU Credits/hour Mem (GiB) Storage Network Performance (Gbps)
    t3.nano 2
    6
    0.5 EBS-Only Up to 5
    t3.micro 2
    12
    1 EBS-Only
    Up to 5
    t3.small 2
    24
    2 EBS-Only
    Up to 5
    t3.medium 2 24
    4 EBS-Only
    Up to 5
    t3.large 2 36
    8 EBS-Only Up to 5
    t3.xlarge 4 96
    16 EBS-Only Up to 5
    t3.2xlarge 8 192
    32 EBS-Only Up to 5

    All instances have the following specs:

    Use Cases:

    Micro-services, low-latency interactive applications, small and medium databases, virtual desktops, development environments, code repositories, and business-critical applications

  • T2
  • T2 instances are Burstable Performance Instances that provide a baseline level of CPU performance with the ability to burst above the baseline.

    T2 Unlimited instances can sustain high CPU performance for as long as a workload needs it. For most general-purpose workloads, T2 Unlimited instances will provide ample performance without any additional charges. If the instance needs to run at higher CPU utilization for a prolonged period, it can also do so at a flat additional charge of 5 cents per vCPU-hour.

    The baseline performance and ability to burst are governed by CPU Credits. T2 instances receive CPU Credits continuously at a set rate depending on the instance size, accumulating CPU Credits when they are idle, and consuming CPU credits when they are active. T2 instances are a good choice for a variety of general-purpose workloads including micro-services, low-latency interactive applications, small and medium databases, virtual desktops, development, build and stage environments, code repositories, and product prototypes. For more information see Burstable Performance Instances.

    Features:

    • High frequency Intel Xeon processors
    • Burstable CPU, governed by CPU Credits, and consistent baseline performance
    • Lowest-cost general purpose instance type, and Free Tier eligible*
    • Balance of compute, memory, and network resources

    * t2.micro only. If configured as T2 Unlimited, charges may apply if average CPU utilization exceeds the baseline of the instance. See documentation for more details.

    Model vCPU* CPU Credits / hour
    Mem (GiB)  Storage
    Network Performance
    t2.nano 1 3 0.5 EBS-Only Low
    t2.micro 1 6 1 EBS-Only
    Low to Moderate
    t2.small 1 12 2 EBS-Only
    Low to Moderate
    t2.medium 2 24 4 EBS-Only
    Low to Moderate
    t2.large 2 36 8 EBS-Only Low to Moderate
    t2.xlarge 4 54 16 EBS-Only Moderate
    t2.2xlarge 8 81 32 EBS-Only Moderate

    All instances have the following specs:

    • Intel AVX†, Intel Turbo†
    • t2.nano, t2.micro, t2.small, t2.medium have up to 3.3 GHz Intel Scalable Processor
    • t2.large, t2.xlarge, and t2.2xlarge have up to 3.0 GHz Intel Scalable Processor

    Use Cases

    Websites and web applications, development environments, build servers, code repositories, micro services, test and staging environments, and line of business applications.  

  • M5
  • M5 instances are the latest generation of General Purpose Instances. This family provides a balance of compute, memory, and network resources, and is a good choice for many applications.

    Features:

    • 2.5 GHz Intel Xeon® Platinum 8175 processors with new Intel Advanced Vector Extension (AXV-512) instruction set
    • New larger instance size, m5.24xlarge, offering 96 vCPUs and 384 GiB of memory
    • Up to 25 Gbps network bandwidth using Enhanced Networking
    • Requires HVM AMIs that include drivers for ENA and NVMe
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • Instance storage offered via EBS or NVMe SSDs that are physically attached to the host server
    • With M5d instances, local NVMe-based SSDs are physically connected to the host server and provide block-level storage that is coupled to the lifetime of the M5 instance
    Model vCPU* Mem (GiB) Storage (GiB) Dedicated EBS Bandwidth (Mbps) Network Performance (Gbps)
    m5.large 2 8 EBS-only Up to 3,500 Up to 10
    m5.xlarge 4 16 EBS-only Up to 3,500 Up to 10
    m5.2xlarge 8 32 EBS-only Up to 3,500 Up to 10
    m5.4xlarge 16 64 EBS-only 3,500 Up to 10
    m5.12xlarge 48 192 EBS-only 7,000 10
    m5.24xlarge 96 384 EBS-only 14,000 25
    m5d.large 2 8 1 x 75  NVMe SSD
    Up to 3,500 Up to 10
    m5d.xlarge 4 16 1 x 150  NVMe SSD Up to 3,500 Up to 10
    m5d.2xlarge 8 32 1 x 300  NVMe SSD Up to 3,500 Up to 10
    m5d.4xlarge 16 64 2 x 300  NVMe SSD 3,500 Up to 10
    m5d.12xlarge 48 192 2 x 900  NVMe SSD 7,000 10
    m5d.24xlarge 96 384 4 x 900  NVMe SSD 14,000 25

    All instances have the following specs:

    Use Cases

    Small and mid-size databases, data processing tasks that require additional memory, caching fleets, and for running backend servers for SAP, Microsoft SharePoint, cluster computing, and other enterprise applications

  • M5a
  • M5a instances are the latest generation of General Purpose Instances. This family provides a balance of compute, memory, and network resources, and is a good choice for many applications.

    Features:

    • AMD EPYC 7000 series processors with an all core turbo clock speed of 2.5 GHz
    • New larger instance size, m5.24xlarge, offering 96 vCPUs and 384 GiB of memory
    • Up to 20 Gbps network bandwidth using Enhanced Networking
    • Requires HVM AMIs that include drivers for ENA and NVMe
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • Instance storage offered via EBS-only
    Model vCPU* Mem (GiB) Storage Dedicated EBS Bandwidth (Mbps) Network Performance (Gbps)
    m5a.large 2 8 EBS-only Up to 2,120 Up to 10
    m5a.xlarge 4 16 EBS-only Up to 2,120 Up to 10
    m5a.2xlarge 8 32 EBS-only Up to 2,120 Up to 10
    m5a.4xlarge 16 64 EBS-only 2,120 Up to 10
    m5a.12xlarge 48 192 EBS-only 5,000 10
    m5a.24xlarge 96 384 EBS-only 10,000 20

    All instances have the following specs:

    Use Cases

    Small and mid-size databases, data processing tasks that require additional memory, caching fleets, and for running backend servers for SAP, Microsoft SharePoint, cluster computing, and other enterprise applications

  • M4
  • M4 instances provide a balance of compute, memory, and network resources, and it is a good choice for many applications.

    Features:

    • 2.3 GHz Intel Xeon® E5-2686 v4 (Broadwell) processors or 2.4 GHz Intel Xeon® E5-2676 v3 (Haswell) processors
    • EBS-optimized by default at no additional cost
    • Support for Enhanced Networking
    • Balance of compute, memory, and network resources
    Model vCPU* Mem (GiB) Storage Dedicated EBS Bandwidth (Mbps) Network Performance
    m4.large 2 8 EBS-only 450 Moderate
    m4.xlarge 4 16 EBS-only 750 High
    m4.2xlarge 8 32 EBS-only 1,000 High
    m4.4xlarge 16 64 EBS-only 2,000 High
    m4.10xlarge 40 160 EBS-only 4,000 10 Gigabit
    m4.16xlarge 64 256 EBS-only 10,000 25 Gigabit

    All instances have the following specs:

    Use Cases

    Small and mid-size databases, data processing tasks that require additional memory, caching fleets, and for running backend servers for SAP, Microsoft SharePoint, cluster computing, and other enterprise applications.

  • T3a (Coming Soon)
  • T3a instances are the next generation burstable general-purpose instance type that provide a baseline level of CPU performance with the ability to burst CPU usage at any time for as long as required. T3a instances offer a balance of compute, memory, and network resources and are designed for applications with moderate CPU usage that experience temporary spikes in use.

    T3a instances accumulate CPU credits when a workload is operating below baseline threshold. Each earned CPU credit provides the T3a instance the opportunity to burst with the performance of a full CPU core for one minute when needed. T3a instances can burst at any time for as long as required in Unlimited mode.

    Features:

    • Burstable CPU, governed by CPU Credits, and consistent baseline performance
    • Unlimited mode by default to ensure performance during peak periods and Standard mode option for a predictable monthly cost
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • T3a features 2.5 GHz AMD EPYC 7000 series processors that offer customers a 10% cost savings over T3 instances
    Model vCPU* CPU Credits/hour Mem (GiB) Storage Network Performance (Gbps)
    t3a.nano 2
    6
    0.5 EBS-Only Up to 5
    t3a.micro 2
    12
    1 EBS-Only
    Up to 5
    t3a.small 2
    24
    2 EBS-Only
    Up to 5
    t3a.medium 2 24
    4 EBS-Only
    Up to 5
    t3a.large 2 36
    8 EBS-Only Up to 5
    t3a.xlarge 4 96
    16 EBS-Only Up to 5
    t3a.2xlarge 8 192
    32 EBS-Only Up to 5

    All instances have the following specs:

    Use Cases:

    Micro-services, low-latency interactive applications, small and medium databases, virtual desktops, development environments, code repositories, and business-critical applications

Each vCPU is a thread of either an Intel Xeon core or an AMD EPYC core, except for T2 and m3.medium.

† AVX, AVX2, and Enhanced Networking are only available on instances launched with HVM AMIs.

* This is the default and maximum number of vCPUs available for this instance type. You can specify a custom number of vCPUs when launching this instance type. For more details on valid vCPU counts and how to start using this feature, visit the Optimize CPUs documentation page here.

** These M4 instances may launch on an Intel Xeon E5-2686 v4 (Broadwell) processor.  

Compute Optimized

  • C5
  • C5 instances are optimized for compute-intensive workloads and deliver very cost-effective high performance at a low price per compute ratio.

    Features:

    • 3.0 GHz Intel Xeon Platinum processors with new Intel Advanced Vector Extension 512 (AVX-512) instruction set
    • Run each core at up to 3.5 GHz using Intel Turbo Boost Technology
    • New larger instance size, c5.18xlarge, offering 72 vCPUs and 144 GiB of memory
    • Up to 25 Gbps of network bandwidth using Elastic Network Adapter (ENA)-based Enhanced Networking
    • Requires HVM AMIs that include drivers for ENA and NVMe
    • Instance storage offered via EBS or NVMe SSDs that are physically attached to the host server
    • With new C5d instances, local NVMe-based SSDs are physically connected to the host server and provide block-level storage that is coupled to the lifetime of the C5 instance
    Model vCPU* Mem (GiB) Storage (GiB) Dedicated EBS Bandwidth (Mbps) Network Performance (Gbps)
    c5.large 2 4 EBS-Only Up to 3,500 Up to 10
    c5.xlarge 4 8 EBS-Only Up to 3,500 Up to 10
    c5.2xlarge 8 16 EBS-Only Up to 3,500 Up to 10
    c5.4xlarge 16 32 EBS-Only 3,500 Up to 10
    c5.9xlarge 36 72 EBS-Only 7,000 10
    c5.18xlarge 72 144 EBS-Only 14,000 25
    c5d.large 2 4 1 x 50 NVMe SSD Up to 3,500 Up to 10
    c5d.xlarge 4 8 1 x 100 NVMe SSD Up to 3,500 Up to 10
    c5d.2xlarge 8 16 1 x 200 NVMe SSD Up to 3,500 Up to 10
    c5d.4xlarge 16 32 1 x 400 NVMe SSD 3,500 Up to 10
    c5d.9xlarge 36 72 1 x 900 NVMe SSD 7,000 10
    c5d.18xlarge 72 144 2 x 900 NVMe SSD 14,000 25

    All instances have the following specs:

    Use Cases

    High performance web servers, scientific modelling, batch processing, distributed analytics, high-performance computing (HPC), machine/deep learning inference, ad serving, highly scalable multiplayer gaming, and video encoding.

  • C4
  • C4 instances are optimized for compute-intensive workloads and deliver very cost-effective high performance at a low price per compute ratio.

    Features:

    • High frequency Intel Xeon E5-2666 v3 (Haswell) processors optimized specifically for EC2
    • Default EBS-optimized for increased storage performance at no additional cost
    • Higher networking performance with Enhanced Networking supporting Intel 82599 VF
    • Requires Amazon VPC, Amazon EBS and 64-bit HVM AMIs
    Model vCPU* Mem (GiB) Storage Dedicated EBS Bandwidth (Mbps) Network Performance
    c4.large 2 3.75 EBS-Only 500 Moderate
    c4.xlarge 4 7.5 EBS-Only 750 High
    c4.2xlarge 8 15 EBS-Only 1,000 High
    c4.4xlarge 16 30 EBS-Only 2,000 High
    c4.8xlarge 36 60 EBS-Only 4,000 10 Gigabit

    All instances have the following specs:

    Use Cases

    High performance front-end fleets, web-servers, batch processing, distributed analytics, high performance science and engineering applications, ad serving, MMO gaming, and video-encoding.

Each vCPU is a thread of either an Intel Xeon core or an AMD EPYC core, except for T2 and m3.medium.

† AVX, AVX2, and Enhanced Networking are only available on instances launched with HVM AMIs.

* This is the default and maximum number of vCPUs available for this instance type. You can specify a custom number of vCPUs when launching this instance type. For more details on valid vCPU counts and how to start using this feature, visit the Optimize CPUs documentation page here.

** These M4 instances may launch on an Intel Xeon E5-2686 v4 (Broadwell) processor.  

Memory Optimized

  • R5
  • R5 instances deliver 5% additional memory per vCPU than R4 and the largest size provides 768 GiB of memory. In addition, R5 instances deliver a 10% price per GiB improvement and a ~20% increased CPU performance over R4.

    Features:

    • Up to 768 GiB of memory per instance
    • Intel Xeon Platinum 8000 series (Skylake-SP) processors with a sustained all core Turbo CPU clock speed of up to 3.1 GHz
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • With R5d instances, local NVMe-based SSDs are physically connected to the host server and provide block-level storage that is coupled to the lifetime of the R5 instance
    Model vCPU Mem (GiB) Storage (GiB) Networking Performance (Gbps)
    r5.large 2 16 EBS-Only Up to 10
    r5.xlarge 4 32 EBS-Only Up to 10
    r5.2xlarge 8 64 EBS-Only Up to 10
    r5.4xlarge 16 128 EBS-Only Up to 10
    r5.12xlarge 48 384 EBS-Only 10
    r5.24xlarge 96 768 EBS-Only 25
    r5d.large 2 16 1 x 75 NVMe SSD Up to 10
    r5d.xlarge 4 32 1 x 150 NVMe SSD Up to 10
    r5d.2xlarge 8 64 1 x 300 NVMe SSD Up to 10
    r5d.4xlarge 16 128 2 x 300 NVMe SSD Up to 10
    r5d.12xlarge 48 384 2 x 900 NVMe SSD 10
    r5d.24xlarge 96 768 4 x 900 NVMe SSD 25

    All instances have the following specs:

    Use Cases

    R5 instances are well suited for memory intensive applications such as high performance databases, distributed web scale in-memory caches, mid-size in-memory databases, real time big data analytics, and other enterprise applications.

  • R5a
  • R5a instances deliver 5% additional memory per vCPU than R4 and the largest size provides 768 GiB of memory. In addition, R5a instances deliver a 10% price per GiB improvement and a ~20% increased CPU performance over R4.

    Features:

    • Up to 768 GiB of memory per instance
    • AMD EPYC 7000 series processors with an all core turbo clock speed of 2.5 GHz
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
     Model vCPU Mem (GiB) Storage Networking Performance (Gbps)
    r5a.large 2 16 EBS-Only Up to 10
    r5a.xlarge 4 32 EBS-Only Up to 10
    r5a.2xlarge 8 64 EBS-Only Up to 10
    r5a.4xlarge 16 128 EBS-Only Up to 10
    r5a.12xlarge 48 384 EBS-Only 10
    r5a.24xlarge 96 768 EBS-Only 20

    All instances have the following specs:

    Use Cases

    R5a instances are well suited for memory intensive applications such as high performance databases, distributed web scale in-memory caches, mid-size in-memory databases, real time big data analytics, and other enterprise applications.

  • R4
  • R4 instances are optimized for memory-intensive applications and offer better price per GiB of RAM than R3.

    Features:

    • High Frequency Intel Xeon E5-2686 v4 (Broadwell) processors
    • DDR4 Memory
    • Support for Enhanced Networking
    Model vCPU Mem (GiB) Storage Networking Performance (Gbps)
    r4.large 2 15.25 EBS-Only Up to 10
    r4.xlarge 4 30.5 EBS-Only Up to 10
    r4.2xlarge 8 61 EBS-Only Up to 10
    r4.4xlarge 16 122 EBS-Only Up to 10
    r4.8xlarge 32 244 EBS-Only 10
    r4.16xlarge 64 488 EBS-Only 25

    All instances have the following specs:

    Use Cases

    High performance databases, data mining & analysis, in-memory databases, distributed web scale in-memory caches, applications performing real-time processing of unstructured big data, Hadoop/Spark clusters, and other enterprise applications.

  • X1e
  • X1e instances are optimized for high-performance databases, in-memory databases and other memory intensive enterprise applications. X1e instances offer one of the lowest price per GiB of RAM among Amazon EC2 instance types.

    Features:

    • High frequency Intel Xeon E7-8880 v3 (Haswell) processors
    • One of the lowest prices per GiB of RAM
    • Up to 3,904 GiB of DRAM-based instance memory
    • SSD instance storage for temporary block-level storage and EBS-optimized by default at no additional cost
    • Ability to control processor C-state and P-state configurations on x1e.32xlarge, x1e.16xlarge and x1e.8xlarge instances
    Model vCPU Mem (GiB) SSD Storage (GB) Dedicated EBS Bandwidth (Mbps) Networking Performance
    x1e.xlarge 4 122 1 x 120 500 Up to 10 Gigabit
    x1e.2xlarge 8 244 1 x 240 1,000 Up to 10 Gigabit
    x1e.4xlarge 16 488 1 x 480 1,750 Up to 10 Gigabit
    x1e.8xlarge 32 976 1 x 960 3,500 Up to 10 Gigabit
    x1e.16xlarge 64 1,952 1 x 1,920 7,000 10 Gigabit
    x1e.32xlarge 128 3,904 2 x 1,920 14,000 25 Gigabit

    All instances have the following specs:

    In addition, x1e.16xlarge and x1e.32xlarge have

    Use Cases

    High performance databases, in-memory databases (e.g. SAP HANA) and memory intensive applications. x1e.32xlarge instance certified by SAP to run next-generation Business Suite S/4HANA, Business Suite on HANA (SoH), Business Warehouse on HANA (BW), and Data Mart Solutions on HANA on the AWS cloud.

  • X1
  • X1 instances are optimized for large-scale, enterprise-class and in-memory applications, and offer one of the lowest price per GiB of RAM among Amazon EC2 instance types.

    Features:

    • High frequency Intel Xeon E7-8880 v3 (Haswell) processors
    • One of the lowest prices per GiB of RAM
    • Up to 1,952 GiB of DRAM-based instance memory
    • SSD instance storage for temporary block-level storage and EBS-optimized by default at no additional cost
    • Ability to control processor C-state and P-state configuration
    Model vCPU Mem (GiB) SSD Storage (GB) Dedicated EBS Bandwidth (Mbps) Network Performance
    x1.16xlarge 64 976 1 x 1,920 7,000 10 Gigabit
    x1.32xlarge 128 1,952 2 x 1,920 14,000 25 Gigabit

    All instances have the following specs:

    Use Cases

    In-memory databases (e.g. SAP HANA), big data processing engines (e.g. Apache Spark or Presto), high performance computing (HPC). Certified by SAP to run Business Warehouse on HANA (BW), Data Mart Solutions on HANA, Business Suite on HANA (SoH), Business Suite S/4HANA.

  • High Memory
  • High memory instances are purpose built to run large in-memory databases, including production deployments of SAP HANA, in the cloud.

    Features:

    • Latest generation Intel® Xeon® Platinum 8176M (Skylake) processors
    • 6, 9, and 12 TiB of instance memory, the largest of any EC2 instance
    • Bare metal performance with direct access to host hardware
    • EBS-optimized by default at no additional cost
    • Available in Amazon Virtual Private Clouds (VPCs)
    Model Logical Proc* Mem (TiB) Network Perf. (Gbps) Dedicated EBS Bandwidth (Gbps) Network Performance
    u-6tb1.metal 448 6 25 14 25 Gigabit
    u-9tb1.metal 448 9 25 14 25 Gigabit
    u-12tb1.metal 448 12 25 14 25 Gigabit

    * Each logical processor is a hyperthread on 224 cores

    All instances have the following specs:

    Use Cases

    Ideal for running large enterprise databases, including production installations of SAP HANA in-memory database in the cloud. Certified by SAP for running Business Suite on HANA, the next-generation Business Suite S/4HANA, Data Mart Solutions on HANA, Business Warehouse on HANA, and SAP BW/4HANA in production environments.

  • z1d
  • Amazon EC2 z1d instances offer both high compute capacity and a high memory footprint. High frequency z1d instances deliver a sustained all core frequency of up to 4.0 GHz, the fastest of any cloud instance.

    Features:

    • A custom Intel® Xeon® Scalable processor with a sustained all core frequency of up to 4.0 GHz
    • Up to 1.8TB of instance storage
    • High memory with up to 384 GiB of RAM
    • Powered by the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor
    • With z1d instances, local NVMe-based SSDs are physically connected to the host server and provide block-level storage that is coupled to the lifetime of the z1d instance
    Model vCPU Mem (GiB) Networking Performance SSD Storage (GB)
    z1d.large 2 16 Up to 10 Gigabit 1 x 75 NVMe SSD
    z1d.xlarge 4 32 Up to 10 Gigabit 1 x 150 NVMe SSD
    z1d.2xlarge 8 64 Up to 10 Gigabit 1 x 300 NVMe SSD
    z1d.3xlarge 12 96 Up to 10 Gigabit 1 x 450 NVMe SSD
    z1d.6xlarge 24 192 10 Gigabit 1 x 900 NVMe SSD
    z1d.12xlarge 48 384 25 Gigabit 2 x 900 NVMe SSD

    All instances have the following specs:

    Use Cases

    Ideal for electronic design automation (EDA) and certain relational database workloads with high per-core licensing costs.

Note: u-6tb1.metal, u-9tb1.metal, and u-12tb1.metal provide 448 logical processors on 224 cores

Accelerated Computing

  • P3
  • P3 instances are the latest generation of general purpose GPU instances.

    Features:

    • Up to 8 NVIDIA Tesla V100 GPUs, each pairing 5,120 CUDA Cores and 640 Tensor Cores
    • High frequency Intel Xeon E5-2686 v4 (Broadwell) processors
    • Supports NVLink for peer-to-peer GPU communication
    • Provide Enhanced Networking using Elastic Network Adapter with up to 25 Gbps of aggregate network bandwidth within a Placement Group
    Model GPUs vCPU Mem (GiB) GPU Mem (GiB) GPU P2P Networking Performance
    p3.2xlarge 1 8 61 16 - Up to 10 Gigabit
    p3.8xlarge 4 32 244 64 NVLink 10 Gigabit
    p3.16xlarge 8 64 488 128 NVLink 25 Gigabit

    All instancess have the following specs:

    Use Cases

    Machine/Deep learning, high performance computing, computational fluid dynamics, computational finance, seismic analysis, speech recognition, autonomous vehicles, drug discovery.

  • P2
  • P2 instances are intended for general-purpose GPU compute applications.

    Features:

    • High frequency Intel Xeon E5-2686 v4 (Broadwell) processors
    • High-performance NVIDIA K80 GPUs, each with 2,496 parallel processing cores and 12GiB of GPU memory
    • Supports GPUDirect™ for peer-to-peer GPU communications
    • Provides Enhanced Networking using Elastic Network Adapter (ENA) with up to 25 Gbps of aggregate network bandwidth within a Placement Group
    • EBS-optimized by default at no additional cost
    Model GPUs vCPU Mem (GiB) GPU Memory (GiB) Network Performance
    p2.xlarge 1 4 61 12 High
    p2.8xlarge 8 32 488 96 10 Gigabit
    p2.16xlarge 16 64 732 192 25 Gigabit

    All instances have the following specs:

    Use Cases

    Machine learning, high performance databases, computational fluid dynamics, computational finance, seismic analysis, molecular modeling, genomics, rendering, and other server-side GPU compute workloads.

  • G3
  • G3 instances are optimized for graphics-intensive applications.

    Features:

    • High frequency Intel Xeon E5-2686 v4 (Broadwell) processors
    • NVIDIA Tesla M60 GPUs, each with 2048 parallel processing cores and 8 GiB of video memory
    • Enables NVIDIA GRID Virtual Workstation features, including support for 4 monitors with resolutions up to 4096x2160. Each GPU included in your instance is licensed for one “Concurrent Connected User"
    • Enables NVIDIA GRID Virtual Application capabilities for application virtualization software like Citrix XenApp Essentials and VMware Horizon, supporting up to 25 concurrent users per GPU
    • Each GPU features an on-board hardware video encoder designed to support up to 10 H.265 (HEVC) 1080p30 streams and up to 18 H.264 1080p30 streams, enabling low-latency frame capture and encoding, and high-quality interactive streaming experiences
    • Enhanced Networking using the Elastic Network Adapter (ENA) with 25 Gbps of aggregate network bandwidth within a Placement Group
    Model GPUs vCPU Mem (GiB) GPU Memory (GiB) Network Performance
    g3s.xlarge 1 4 30.5 8 Up to 10 Gigabit
    g3.4xlarge 1 16 122 8 Up to 10 Gigabit
    g3.8xlarge 2 32 244 16 10 Gigabit
    g3.16xlarge 4 64 488 32 25 Gigabit

    All instances have the following specs:

    Use Cases

    3D visualizations, graphics-intensive remote workstation, 3D rendering, application streaming, video encoding, and other server-side graphics workloads.

  • F1
  • F1 instances offer customizable hardware acceleration with field programmable gate arrays (FPGAs).

    Instances Features:

    • High frequency Intel Xeon E5-2686 v4 (Broadwell) processors
    • NVMe SSD Storage
    • Support for Enhanced Networking

    FPGA Features:

    • Xilinx Virtex UltraScale+ VU9P FPGAs
    • 64 GiB of ECC-protected memory on 4x DDR4
    • Dedicated PCI-Express x16 interface
    • Approximately 2.5 million logic elements
    • Approximately 6,800 Digital Signal Processing (DSP) engines
    • FPGA Developer AMI
    Model FPGAs vCPU Mem (GiB) SSD Storage (GB) Networking Performance
    f1.2xlarge 1 8 122 470 Up to 10 Gigabit
    f1.4xlarge 2 16 244 940 Up to 10 Gigabit
    f1.16xlarge 8 64 976 4 x 940 25 Gigabit

    For f1.16xlarge instances, the dedicated PCI-e fabric lets the FPGAs share the same memory space and communicate with each other across the fabric at up to 12 Gbps in each direction. The FPGAs within the f1.16xlarge share access to a 400 Gbps bidirectional ring for low-latency, high bandwidth communication.

    All instances have the following specs:

    Use Cases

    Genomics research, financial analytics, real-time video processing, big data search and analysis, and security.

Storage Optimized

  • H1
  • I3
  • D2
  • H1
  • H1 instances feature up to 16 TB of HDD-based local storage, deliver high disk throughput, and a balance of compute and memory.

    Features:

    • Powered by 2.3 GHz Intel® Xeon® E5 2686 v4 processors (codenamed Broadwell)
    • Up to 16TB of HDD storage
    • High disk throughput
    • ENA enabled Enhanced Networking up to 25 Gbps
    Model vCPU* Mem (GiB) Networking Performance Storage (GB)
    h1.2xlarge 8 32 Up to 10 Gigabit 1 x 2,000 HDD
    h1.4xlarge 16 64 Up to 10 Gigabit 2 x 2,000 HDD
    h1.8xlarge 32 128 10 Gigabit 4 x 2,000 HDD
    h1.16xlarge 64 256 25 Gigabit 8 x 2,000 HDD

    All instances have the following specs:

    Use Cases

    MapReduce-based workloads, distributed file systems such as HDFS and MapR-FS, network file systems, log or data processing applications such as Apache Kafka, and big data workload clusters.

  • I3
  • This instance family provides Non-Volatile Memory Express (NVMe) SSD-backed instance storage optimized for low latency, very high random I/O performance, high sequential read throughput and provide high IOPS at a low cost. I3 also offers Bare Metal instances (i3.metal), powered by the Nitro System, for non-virtualized workloads, workloads that benefit from access to physical resources, or workloads that may have license restrictions.

    Features:

    • High Frequency Intel Xeon E5-2686 v4 (Broadwell) Processors with base frequency of 2.3 GHz
    • Up to 25 Gbps of network bandwidth using Elastic Network Adapter (ENA)-based Enhanced Networking
    • High Random I/O performance and High Sequential Read throughput
    • Support bare metal instance size for workloads that benefit from direct access to physical processor and memory
    Model vCPU* Mem (GiB) Networking Performance (Gbps) Storage (TB)
    i3.large 2 15.25 Up to 10 1 x 0.475 NVMe SSD
    i3.xlarge 4 30.5 Up to 10 1 x 0.95 NVMe SSD
    i3.2xlarge 8 61 Up to 10 1 x 1.9 NVMe SSD
    i3.4xlarge 16 122 Up to 10 2 x 1.9 NVMe SSD
    i3.8xlarge 32 244 10 4 x 1.9 NVMe SSD
    i3.16xlarge 64 488 25 8 x 1.9 NVMe SSD
    i3.metal 72* 512 25 8 x 1.9 NVMe SSD

    All instances have the following specs:

    Use Cases

    NoSQL databases (e.g. Cassandra, MongoDB, Redis), in-memory databases (e.g. Aerospike), scale-out transactional databases, data warehousing, Elasticsearch, analytics workloads.

  • D2
  • D2 instances feature up to 48 TB of HDD-based local storage, deliver high disk throughput, and offer the lowest price per disk throughput performance on Amazon EC2.

    Features:

    • High-frequency Intel Xeon E5-2676 v3 (Haswell) processors
    • HDD storage
    • Consistent high performance at launch time
    • High disk throughput
    • Support for Enhanced Networking
    Model vCPU* Mem (GiB) Storage (GB) Network Performance
    d2.xlarge 4 30.5 3 x 2000 HDD Moderate
    d2.2xlarge 8 61 6 x 2000 HDD High
    d2.4xlarge 16 122 12 x 2000 HDD High
    d2.8xlarge 36 244 24 x 2000 HDD 10 Gigabit

    All instances have the following specs:

    Use Cases

    Massively Parallel Processing (MPP) data warehousing, MapReduce and Hadoop distributed computing, distributed file systems, network file systems, log or data-processing applications.

** i3.metal provides 72 logical processors on 36 physical cores

Looking for previous generation instances that were not listed here? Please see the Previous Generation Instances page.

Each vCPU is a thread of either an Intel Xeon core or an AMD EPYC core, except for T2 and m3.medium.

† AVX, AVX2, and Enhanced Networking are only available on instances launched with HVM AMIs.

* This is the default and maximum number of vCPUs available for this instance type. You can specify a custom number of vCPUs when launching this instance type. For more details on valid vCPU counts and how to start using this feature, visit the Optimize CPUs documentation page here.

Instance Features

Amazon EC2 instances provide a number of additional features to help you deploy, manage, and scale your applications.

Burstable Performance Instances

Amazon EC2 allows you to choose between Fixed Performance Instances (e.g. M5, C5, and R5) and Burstable Performance Instances (e.g. T3). Burstable Performance Instances provide a baseline level of CPU performance with the ability to burst above the baseline.

T Unlimited instances can sustain high CPU performance for as long as a workload needs it. For most general-purpose workloads, T Unlimited instances will provide ample performance without any additional charges. The hourly T instance price automatically covers all interim spikes in usage when the average CPU utilization of a T instance is at or less than the baseline over a 24-hour window. If the instance needs to run at higher CPU utilization for a prolonged period, it can do so at a flat additional charge of 5 cents per vCPU-hour.

T instances’ baseline performance and ability to burst are governed by CPU Credits. Each T instance receives CPU Credits continuously, the rate of which depends on the instance size. T instances accrue CPU Credits when they are idle, and use CPU credits when they are active. A CPU Credit provides the performance of a full CPU core for one minute.

For example, a t2.small instance receives credits continuously at a rate of 12 CPU Credits per hour. This capability provides baseline performance equivalent to 20% of a CPU core (20% x 60 mins = 12 mins). If the instance does not use the credits it receives, they are stored in its CPU Credit balance up to a maximum of 288 CPU Credits. When the t2.small instance needs to burst to more than 20% of a core, it draws from its CPU Credit balance to handle this surge automatically.

With T2 Unlimited enabled, the t2.small instance can burst above the baseline even after its CPU Credit balance is drawn down to zero. For a vast majority of general purpose workloads where the average CPU utilization is at or below the baseline performance, the basic hourly price for t2.small covers all CPU bursts. If the instance happens to run at an average 25% CPU utilization (5% above baseline) over a period of 24 hours after its CPU Credit balance is drawn to zero, it will be charged an additional 6 cents (5 cents/vCPU-hour x 1 vCPU x 5% x 24 hours).

Many applications such as web servers, developer environments and small databases don’t need consistently high levels of CPU, but benefit significantly from having full access to very fast CPUs when they need them. T instances are engineered specifically for these use cases. If you need consistently high CPU performance for applications such as video encoding, high volume websites or HPC applications, we recommend you use Fixed Performance Instances. T instances are designed to perform as if they have dedicated high speed Intel cores available when your application really needs CPU performance, while protecting you from the variable performance or other common side-effects you might typically see from over-subscription in other environments.

Multiple Storage Options

Amazon EC2 allows you to choose between multiple storage options based on your requirements. Amazon EBS is a durable, block-level storage volume that you can attach to a single, running Amazon EC2 instance. You can use Amazon EBS as a primary storage device for data that requires frequent and granular updates. For example, Amazon EBS is the recommended storage option when you run a database on Amazon EC2. Amazon EBS volumes persist independently from the running life of an Amazon EC2 instance. Once a volume is attached to an instance you can use it like any other physical hard drive. Amazon EBS provides three volume types to best meet the needs of your workloads: General Purpose (SSD), Provisioned IOPS (SSD), and Magnetic. General Purpose (SSD) is the new, SSD-backed, general purpose EBS volume type that we recommend as the default choice for customers. General Purpose (SSD) volumes are suitable for a broad range of workloads, including small to medium sized databases, development and test environments, and boot volumes. Provisioned IOPS (SSD) volumes offer storage with consistent and low-latency performance, and are designed for I/O intensive applications such as large relational or NoSQL databases. Magnetic volumes provide the lowest cost per gigabyte of all EBS volume types. Magnetic volumes are ideal for workloads where data is accessed infrequently, and applications where the lowest storage cost is important.

Many Amazon EC2 instances can also include storage from disks that are physically attached to the host computer. This disk storage is referred to as instance store. Instance store provides temporary block-level storage for Amazon EC2 instances. The data on an instance store volume persists only during the life of the associated Amazon EC2 instance.

In addition to block level storage via Amazon EBS or instance store, you can also use Amazon S3 for highly durable, highly available object storage. Learn more about Amazon EC2 storage options from the Amazon EC2 documentation.

EBS-optimized Instances

For an additional, low, hourly fee, customers can launch selected Amazon EC2 instances types as EBS-optimized instances. For C5, C4, M5, M4, P3, P2, G3, and D2 instances, this feature is enabled by default at no additional cost. EBS-optimized instances enable EC2 instances to fully use the IOPS provisioned on an EBS volume. EBS-optimized instances deliver dedicated throughput between Amazon EC2 and Amazon EBS, with options between 500 and 4,000 Megabits per second (Mbps) depending on the instance type used. The dedicated throughput minimizes contention between Amazon EBS I/O and other traffic from your EC2 instance, providing the best performance for your EBS volumes. EBS-optimized instances are designed for use with both Standard and Provisioned IOPS Amazon EBS volumes. When attached to EBS-optimized instances, Provisioned IOPS volumes can achieve single digit millisecond latencies and are designed to deliver within 10% of the provisioned IOPS performance 99.9% of the time. We recommend using Provisioned IOPS volumes with EBS-optimized instances or instances that support cluster networking for applications with high storage I/O requirements.

Cluster Networking

Select EC2 instances support cluster networking when launched into a common cluster placement group. A cluster placement group provides low-latency networking between all instances in the cluster. The bandwidth an EC2 instance can utilize depends on the instance type and its networking performance specification. Inter instance traffic within the same region can utilize up to 5 Gbps for single-flow and up to 25 Gbps for multi-flow traffic in each direction (full duplex). Traffic to and from S3 buckets in the same region can also utilize all available instance aggregate bandwidth. When launched in a placement group, instances can utilize up to 10 Gbps for single-flow traffic and up to 25 Gbps for multi-flow traffic. Network traffic to the Internet is limited to 5 Gbps (full duplex). Cluster networking is ideal for high performance analytics systems and many science and engineering applications, especially those using the MPI library standard for parallel programming.

Intel Processor Features
intelinside_150

Amazon EC2 instances that feature an Intel processor may provide access to the following processor features:

  • Intel AES New Instructions (AES-NI): Intel AES-NI encryption instruction set improves upon the original Advanced Encryption Standard (AES) algorithm to provide faster data protection and greater security. All current generation EC2 instances support this processor feature.
  • Intel Advanced Vector Extensions (Intel AVX, Intel AVX2 and Intel AVX-512): Intel AVX and Intel AVX2 are 256-bit and Intel AVX-512 is a 512-bit instruction set extensions designed for applications that are Floating Point (FP) intensive. Intel AVX instructions improve performance for applications like image and audio/video processing, scientific simulations, financial analytics, and 3D modeling and analysis. These features are only available on instances launched with HVM AMIs.
  • Intel Turbo Boost Technology: Intel Turbo Boost Technology provides more performance when needed. The processor is able to automatically run cores faster than the base operating frequency to help you get more done faster.

Not all processor features are available in all instance types, check out the instance type matrix for more detailed information on which features are available from which instance types.

Measuring Instance Performance

Why should you measure instance performance?

Amazon EC2 allows you to provision a variety of instances types, which provide different combinations of CPU, memory, disk, and networking. Launching new instances and running tests in parallel is easy, and we recommend measuring the performance of applications to identify appropriate instance types and validate application architecture. We also recommend rigorous load/scale testing to ensure that your applications can scale as you intend.

Considerations for Amazon EC2 performance evaluation

Amazon EC2 provides you with a large number of options across ten different instance types, each with one or more size options, organized into six distinct instance families optimized for different types of applications. We recommend that you assess the requirements of your applications and select the appropriate instance family as a starting point for application performance testing. You should start evaluating the performance of your applications by (a) identifying how your application needs compare to different instance families (e.g. is the application compute-bound, memory-bound, etc.?), and (b) sizing your workload to identify the appropriate instance size. There is no substitute for measuring the performance of your full application since application performance can be impacted by the underlying infrastructure or by software and architectural limitations. We recommend application-level testing, including the use of application profiling and load testing tools and services.