Detailed server hardware requirements

This topic describes the server hardware requirements for the Pexip Infinity platform:

Host server hardware requirements

The following table lists the recommended hardware requirements for the Management Node and Conferencing Node (Proxying Edge Nodes and Transcoding Conferencing Nodes) host servers.

  Management Node Transcoding Conferencing Node Proxying Edge Node
Server manufacturer Any

Processor make

(see also Performance considerations)


We recommend 3rd- or 4th-generation Intel Xeon Scalable Series processors (Ice Lake / Sapphire Rapids) Gold 63xx/64xx for Transcoding Conferencing Nodes.

  • Earlier Intel Xeon Scalable Series processors and Intel Xeon E5/E7-v3 and -v4 series process are also supported where newer hardware is not available. Machines based on these architectures will work well for Management and Proxying Edge nodes, we recommend prioritizing the newest hardware for transcoding nodes.
  • Other x86-64 processors from Intel and AMD that support at least the AVX instruction set can be used but are not recommended. Some features are only available on underlying hardware that supports at least the AVX2 instruction set.

Any x86-64 processor which supports at least the AVX instruction set. Most Intel Xeon Scalable Series and Xeon E5/E7-v3 and -v4 processors are suitable.

If a mixture of older and newer hardware is available, we recommend using the older or less capable hardware for proxying nodes and the newest or most powerful for transcoding nodes.

Processor instruction set Any AVX2 or AVX512 (AVX is also supported) AVX
Processor architecture x86-64
Processor speed 2.0 GHz

2.6 GHz (or faster) base clock speed if using Hyper-Threading on 3rd-generation Intel Xeon Scalable Series (Ice Lake) processors or newer.

  • 2.8 GHz+ for older Intel Xeon processors where Hyper-Threading is in use
  • 2.3 GHz+ where Hyper-Threading is not in use
2.0 GHz
No. of vCPUs *
Minimum 4 Minimum 4 vCPU per node

Maximum 48 vCPU per node, i.e. 24 cores if using Hyper-Threading

  • Higher core-counts are possible on fast processors: up to 56 vCPU has been tested successfully
  • Slow (under 2.3GHz) processors may require lower core counts

Minimum 4 vCPU per node

Maximum 8 vCPU per node

Processor cache no minimum 20 MB or greater no minimum
Total RAM * Minimum 4 GB

(minimum 1 GB RAM for each Management Node vCPU)

1 GB RAM per vCPU, so either:

  • 1 GB RAM per physical core (if deploying 1 vCPU per core), or
  • 2 GB RAM per physical core (if using Hyper-Threading and NUMA affinity to deploy 2 vCPUs per core).
1GB RAM per vCPU
RAM makeup Any All channels must be populated with a DIMM, see Memory configuration below. Intel Xeon Scalable series processors support 6 DIMMs per socket and older Xeon E5 series processors support 4 DIMMs per socket. Any
Hardware allocation The host server must not be over-committed (also referred to as over-subscribing or over-allocation) in terms of either RAM or CPU. In other words, the Management Node and Conferencing Nodes each must have dedicated access to their own RAM and CPU cores.
Storage space required 100 GB SSD
  • 500 GB total per server (to allow for snapshots etc.), including:
  • 50 GB minimum per Conferencing Node
  • SSD recommended
  • RAID 1 mirrored storage (recommended)
Although Pexip Infinity will work with SAS drives, we strongly recommend SSDs for both the Management Node and Conferencing Nodes. General VM processes (such as snapshots and backups) and platform upgrades will be faster with SSDs.
GPU No specific hardware cards or GPUs are required.
Network Gigabit Ethernet connectivity from the host server.
Operating System The Pexip Infinity VMs are delivered as VM images (.ova etc.) to be run directly on the hypervisor. No OS should be installed.


(see also Performance considerations)

Recommended hypervisors:

  • VMware ESXi 6.7, 7.0 and 8.0
  • KVM

Supported but not recommended for new deployments:

  • Microsoft Hyper-V 2019

* This does not include the processor and RAM requirements of the hypervisor.

† Sufficient for typical deployments of up to 30 Conferencing Nodes. For deployments with more than 30 Conferencing Nodes, you will need to increase the number of cores and the amount of RAM on the Management Node. Please contact your Pexip authorized support representative or your Pexip Solution Architect for guidance on Management Node sizing specific to your environment.


The number of calls (or ports) that can be achieved per server in a Pexip Infinity deployment will depend on a number of things including the specifications of the particular server and the bandwidth of each call. For more information, see Capacity planning.

As a general indication of capacity: Servers that are older, have slower processors, or have fewer CPUs, will have a lower overall capacity. Newer servers with faster processors will have a greater capacity. The use of NUMA affinity and Hyper-Threading can significantly increase capacity.

Performance considerations

The type of processors and Hypervisors used in your deployment will impact the levels of performance you can achieve. Some known performance considerations are described below.

Intel AVX2 / AVX512 processor instruction set

Pexip Infinity can make full use of the AVX2 and AVX512 instruction set provided by modern Intel processors. This increases the performance of video encoding and decoding.

The VP9 codec is also available for connections to Conferencing Nodes running the AVX2 or later instruction set. VP9 uses around one third less bandwidth for the same resolution when compared to VP8. Note however that VP9 calls consume around 1.25 times the CPU resource (ports) on the Conferencing Node.

AMD processors

We have observed during internal testing that use of AMD processors results in a reduction of capacity (measured by ports per core) of around 40% when compared to an identically configured Intel platform. This is because current AMD processors do not execute advanced instruction sets at the same speed as Intel processors.

AMD processors older than 2012 may not perform sufficiently and are not recommended for use with the Pexip Infinity platform.

Memory configuration

Memory must be distributed on the different memory channels (i.e. 6 to 8 channels per socket on the Xeon Scalable series, and 4 channels per socket on the Xeon E5 and E7 series).

There must be an equal amount of memory per socket, and all sockets must have all memory channels populated (you do not need to populate all slots in a channel, one DIMM per channel is sufficient). Do not, for example, use two large DIMMs rather than four lower-capacity DIMMs — using only two per socket will result in half the memory bandwidth, since the memory interface is designed to read up from four DIMMs at the same time in parallel

The smaller Intel Xeon Scalable Possessors (Silver and Bronze series) can be safely deployed with 4 memory channels per socket, but we do not recommend the Silver and Bronze series for most Pexip workloads.

Example - dual socket, 6 channels

Intel Xeon Scalable series dual socket system:

  • Each socket has 6 channels
  • All 6 channels must be populated with a DIMM
  • Both sockets must have the same configuration

Therefore for a dual socket Gold 61xx you need 12 identical memory DIMMs.

Example - dual socket, 4 channels

Xeon E5-2600 dual socket system:

  • Each socket has 4 channels
  • All 4 channels must be populated with a DIMM
  • Both sockets must have the same configuration

Therefore for a dual socket E5-2600 you need 8 identical memory DIMMs.