Microsoft Azure Instance Types

Bs-series are economical virtual machines that provide a low-cost option for workloads that typically run at a low to moderate baseline CPU performance, but sometimes need to burst to significantly higher CPU performance when the demand rises. These workloads don’t require the use of the full CPU all the time, but occasionally will need to burst to finish some tasks more quickly. Many applications such as development and test servers, low traffic web servers, small databases, micro services, servers for proof-of-concepts, build servers, and code repositories fit into this model.
Very small temporary storage is included.

The Dav4 and Dasv4 Azure VM-series provide up to 96 vCPUs, 384 GiBs of RAM and 2,400 GiBs of SSD-based temporary storage and feature the AMD EPYC™ 7452 processor.
The "s" variants support "Premium SSD disk storage" and have smaller temporary storage.

The Dads v5-series virtual machines are based on the 3rd Generation AMD EPYCTM 7763v (Milan) processor. This processor's frequency can achieve up to 3.5GHz. The Dads v5 virtual machine sizes feature high performance, large local SSD storage (up to 3,600 GiB) and provide a better value proposition for most general-purpose workloads compared to the prior Das v4 VM generation (e.g., more local SSD capacity and faster local disk IOPS).

The Das v5-series virtual machines are based on the 3rd Generation AMD EPYCTM 7763v (Milan) processor. This processor's frequency can achieve up to 3.5GHz. The Das v5 VM sizes offer a combination of vCPUs and memory able to meet the requirements associated with most production workloads.
The Das v5 virtual machine sizes do not have any temporary storage thus lowering the price of entry.

The Ddv4 series virtual machines are based on the Intel® Xeon® Platinum 8272CL processor. This custom processor runs at a base speed of 2.5Ghz and can achieve up to 3.4Ghz all core turbo frequency. The Ddv4/Ddsv4 virtual machine sizes feature fast, large local SSD storage (up to 2,400 GiB) and are well suited for applications that benefit from low latency, high-speed local storage.

The Ddsv5 series virtual machines are based on the 3rd Generation Intel® Xeon® Platinum 8370C (Ice Lake) processor in a hyper-threaded configuration. The Ddv5 and Ddsv5 virtual machine sizes feature high performance, large local SSD storage (up to 3,600 GiB) and provide a better value proposition for most general-purpose workloads compared to the prior generation (e.g., increased scalability and an upgraded CPU class).

The Dplsv6-series virtual machines are powered by Azure’s first-generation Cobalt 100 processor, delivering outstanding performance for general-purpose workloads. The Azure Cobalt 100 processor operates at 3.4 GHz and provides an entire physical core for each virtual machine vCPU. These virtual machines offer 2 GiB of memory per vCPU and a wide range of vCPU sizes.

The Dplsv5-series and Dpldsv5-series virtual machines are based on the Arm architecture, delivering outstanding price-performance for general-purpose workloads. These virtual machines feature the Ampere® Altra® Arm-based processor operating at 3.0 GHz, which provides an entire physical core for each virtual machine vCPU. These virtual machines offer a range of vCPU sizes, up to 2 GiB of memory per vCPU, and temporary storage options able to meet the requirements of most non-memory-intensive and scale-out workloads such as microservices, small databases, caches, gaming servers, and more.

The Dv5 and Ddv5 series virtual machines feature the 3rd Generation Intel® Xeon® Platinum 8370C (Ice Lake) processor in a hyper-threaded configuration. They can scale up to 96 vCPUs with configurations similar to the Dv4 and Ddv4 series VMs.
They support Azure Premium SSDs and Ultra Disk storage depending on regional availability.

The Eads v5-series virtual machines are based on the 3rd Generation AMD EPYCTM 7763v (Milan) processor. This processor has base frequency of 2.55Ghz and can achieve up to 3.7 GHz. The Eads v5 VM sizes feature up to 672 GiB of RAM, high performance, and large local SSD storage (up to 3,600 GiB.) These virtual machines are ideal for memory-intensive enterprise applications, relational database servers, and in-memory analytics workloads.

The Fsv2-series virtual machines provide 2-GiB of RAM and 8 GB of local temporary storage (SSD) per vCPU(s) and are optimized for compute intensive workloads. The Fsv2-series VMs are hyper-threaded and based on the Intel® Xeon® Platinum 8272CL (second generation Intel® Xeon® Scalable processors), or the Intel Xeon® Platinum 8168 (Skylake) processor.
The Fsv2 VMs can be attached to Premium SSD or Ultra Disk persistent storage.

The Azure Dadsv6-series virtual machines are based on AMD's 4th Generation EPYC™ 9004 processors with a boosted maximum frequency of 3.7GHz. They offer a combination of vCPU, memory, and fast local NVMe temporary storage, making them suitable for most production workloads. Configurations are available with up to 96 vCPUs and 384 GiB of RAM. Disk storage is billed separately.

Dadsv6-series Azure VMs utilize AMD's 4th Generation EPYC™ 9004 processors, achieving a boosted maximum frequency of 3.7GHz. These virtual machines offer a combination of vCPU, memory, and fast local NVMe temporary storage suitable for most production workloads. They are available in sizes up to 96 vCPU and 384 GiB of RAM and support various disk types, although disk storage is billed separately.

The Azure Dasv6-series Virtual Machines are a general-purpose offering utilizing AMD's 4th Generation EPYC™ 9004 processors, capable of reaching boosted frequencies of up to 3.7GHz. These VMs provide a balance of vCPU and memory suitable for most production workloads, with configurations scaling up to 96 vCPUs and 384 GiB of RAM. They offer a compelling value proposition for workloads that do not necessitate local temporary storage.

Dsv6-series virtual machines run on the 5th Generation Intel® Xeon® Platinum 8573C (Emerald Rapids) processor reaching an all-core turbo clock speed of 3.0 GHz. This new processor features Intel® Turbo Boost Technology, Intel® Advanced-Vector Extensions 512 (Intel® AVX-512), and Intel® Advanced Matrix Extensions. These virtual machines offer up to 192 vCPU and 768 GiB of RAM. Dsv6-series virtual machines provide a better performance for most general-purpose workloads compared to the prior generation (for example, increased scalability, upgraded CPU, elevated memory bandwidth, faster remote storage access).

The NCasT4_v3-series virtual machines are powered by Nvidia Tesla T4 GPUs and AMD EPYC 7V12(Rome) CPUs. The VMs feature up to 4 NVIDIA T4 GPUs with 16 GB of memory each, up to 64 non-multithreaded AMD EPYC 7V12 (Rome) processor cores(base frequency of 2.45 GHz, all-cores peak frequency of 3.1 GHz and single-core peak frequency of 3.3 GHz) and 440 GiB of system memory.

The NCads H100 v5-series virtual machines are part of the Azure GPU family designed for Applied AI training and batch inference workloads. Powered by NVIDIA H100 NVL GPUs and 4th-generation AMD EPYC Genoa processors, these instances provide high-performance compute capabilities. They feature up to 2 GPUs with 94GB memory each and up to 96 non-multithreaded processor cores. This series is ideal for GPU-accelerated analytics, video processing, and autonomy model training, supporting high-throughput local NVMe storage and accelerated networking.

NCv3-series VMs are powered by NVIDIA Tesla V100 GPUs. From 6 to 24 Intel Xeon E5-2690 v4 vCPUs.

The ND H200 v5-series is a flagship Azure virtual machine designed for high-end AI training and generative inference. It features eight NVIDIA H200 Tensor Core GPUs with 141GB of HBM3e memory each, providing 4.8 TB/s of bandwidth. Powered by Sapphire Rapids processors, it offers 96 vCPUs and 1850 GiB of RAM. With 3.2 Tb/s of InfiniBand interconnect, it is optimized for large-scale, low-latency AI clusters and complex scientific computing workloads.

The ND H100 v5-series virtual machines are Azure's flagship generative AI infrastructure, designed for massive-scale AI training and inference. These instances feature eight NVIDIA H100 Tensor Core GPUs interconnected via 400 Gb/s NVIDIA Quantum-2 InfiniBand. They are powered by 4th Gen Intel Xeon Scalable processors and provide significant performance leaps for large language models. With high-speed DDR5 memory and local NVMe storage, they deliver the throughput necessary for the most demanding deep learning workloads and high-performance computing applications.

The NVv3-series virtual machines are powered by NVIDIA Tesla M60 GPUs and NVIDIA GRID technology with Intel E5-2690 v4 (Broadwell) CPUs and Intel Hyper-Threading Technology. These virtual machines are targeted for GPU accelerated graphics applications and virtual desktops where customers want to visualize their data, simulate results to view, work on CAD, or render and stream content