'F' family compute optimized VM size series

Article
08/22/2024

Applies to: ✔️ Linux VMs ✔️ Windows VMs ✔️ Flexible scale sets ✔️ Uniform scale sets

The 'F' family of VM size series are one of Azure's compute-optimized VM instances. They're designed for workloads that require high CPU performance, such as batch processing, web servers, analytics, and gaming. Featuring a high CPU-to-memory ratio, F-series VMs are equipped with powerful processors to handle applications that demand more CPU capacity relative to memory. This makes them particularly effective for scenarios where fast and efficient processing is critical, allowing businesses to run their compute-bound applications efficiently and cost-effectively.

Workloads and use cases

Web Servers: F-series VMs are excellent for hosting web servers and applications that require significant compute capability to handle web traffic efficiently without necessarily needing large amounts of memory.

Batch Processing: F-series VMs are ideal for batch jobs and other processing tasks that involve handling large volumes of data or tasks in a queue but are more CPU-intensive than memory-intensive.

Application Servers: Applications that require quick processing and do not have high memory demands can benefit from F-series VMs. These can include medium traffic application servers, back-end servers for enterprise applications, and other similar tasks. Gaming Servers: Due to their high CPU performance, F-series VMs are also suitable for gaming servers where fast processing is critical for a good gaming experience.

Analytics: F-series VMs can be used for data analytics applications that require processing speed to crunch numbers and perform calculations more than they require a large amount of memory.

Series in family

Fsv2-series

The Fsv2-series run on the 3rd Generation Intel® Xeon® Platinum 8370C (Ice Lake), the Intel® Xeon® Platinum 8272CL (Cascade Lake) processors, or the Intel® Xeon® Platinum 8168 (Skylake) processors. It features a sustained all core Turbo clock speed of 3.4 GHz and a maximum single-core turbo frequency of 3.7 GHz. Intel® AVX-512 instructions are new on Intel Scalable Processors. These instructions provide up to a 2X performance boost to vector processing workloads on both single and double precision floating point operations. In other words, they're really fast for any computational workload. Fsv2-series VMs feature Intel® Hyper-Threading Technology.

View the full Fsv2-series page.

Part	Quantity ^{Count Units}	Specs ^{SKU ID, Performance Units, etc.}
Processor	2 - 72 vCPUs	Intel Xeon Platinum 8370C (Ice Lake) [x86-64] Intel Xeon Platinum 8272CL (Cascade Lake) [x86-64] Intel Xeon Platinum 8168 (Skylake) [x86-64]
Memory	4 - 144 GiB
Local Storage	1 Disk	16 - 576 GiB 4000 - 144000 IOPS (RR) 31 - 1152 MBps (RR)
Remote Storage	4 - 32 Disks	3200 - 80000 IOPS 47 - 1100 MBps
Network	2 - 8 NICs	5000 - 30000 Mbps
Accelerators	None

The Fasv6-series utilizes AMD's fourth Generation EPYC™ 9004 processor that can achieve a boosted maximum frequency of 3.7 GHz with up to 320 MB L3 cache. The Fasv6 VM series comes without Simultaneous Multithreading (SMT), meaning a vCPU is now mapped to a full physical core, allowing software processes to run on dedicated and uncontested resources. These new full core VMs suit workloads demanding the highest CPU performance. Fasv6-series offers up to 64 full core vCPUs and 512 GiB of RAM in three 'memory to core' ratios. This series is optimized for scientific simulations, financial and risk analysis, gaming, rendering and other workloads able to take advantage of the exceptional performance. Customers running software licensed on per-vCPU basis can use these VMs to optimize compute costs within their infrastructure.

View the full Fasv6 and Falsv6-series page.

Part	Quantity ^{Count Units}	Specs ^{SKU ID, Performance Units, etc.}
Processor	2 - 64 vCPUs	AMD EPYC 9004 (Genoa) [x86-64]
Memory	8 - 256 GiB
Local Storage	None
Remote Storage	4 - 32 Disks	4000 - 115200 IOPS 90 - 2880 MBps
Network	2 - 8 NICs	12500 - 36000 Mbps
Accelerators	None

The Falsv6-series utilizes AMD's fourth Generation EPYC™ 9004 processor that can achieve a boosted maximum frequency of 3.7 GHz with up to 320 MB L3 cache. The Falsv6 VM series comes without Simultaneous Multithreading (SMT), meaning a vCPU is now mapped to a full physical core, allowing software processes to run on dedicated and uncontested resources. These new full core VMs suit workloads demanding the highest CPU performance. Falsv6-series offers up to 64 full core vCPUs and 512 GiB of RAM in three 'memory to core' ratios. This series is optimized for scientific simulations, financial and risk analysis, gaming, rendering and other workloads able to take advantage of the exceptional performance. Customers running software licensed on per-vCPU basis can use these VMs to optimize compute costs within their infrastructure.

View the full Falsv6-series page.

Part	Quantity ^{Count Units}	Specs ^{SKU ID, Performance Units, etc.}
Processor	2 - 64 vCPUs	AMD EPYC 9004 (Genoa) [x86-64]
Memory	4 - 128 GiB
Local Storage	None
Remote Storage	4 - 32 Disks	4000 - 115200 IOPS 90 - 2880 MBps
Network	2 - 8 NICs	12500 - 36,000 Mbps
Accelerators	None

Previous-generation F family series

For older sizes, see previous generation sizes.

Other size information

List of all available sizes: Sizes

Pricing Calculator: Pricing Calculator

Information on Disk Types: Disk Types

Next steps

Learn more about how Azure compute units (ACU) can help you compare compute performance across Azure SKUs.

Check out Azure Dedicated Hosts for physical servers able to host one or more virtual machines assigned to one Azure subscription.

Learn how to Monitor Azure virtual machines.

Share via