NVIDIA Tesla A16 (16G*4)

The NVIDIA A16, built on the NVIDIA Ampere architecture, combines with NVIDIA virtual GPU (vGPU) software to raise the bar on user experience for graphics-rich virtual desktop infrastructure (VDI). As more organizations turn to remote work as long term strategy, A16 with the NVIDIA Virtual PC (vPC) or Virtual Applications (vApps) software, enables knowledge workers across every industry to maximize productivity with performance indistinguishable from a native PC. NVIDIA A16 delivers up to 2X the user density, compared with the previous generation M10, reducing the amount of hardware resources needed and lowering the total cost of ownership (TCO).
When combined with NVIDIA RTX Virtual Workstation (vWS) software, the A16 enables affordable entry-level virtual workstations ideal for running workloads such as computer-aided design (CAD). The A16 features a unique quad-GPU board design enabling the provisioning of mixed user profile sizes, so IT can support light virtual PC workloads as well as users with larger memory and graphics requirements. Mixing user types on a board is also supported, enabling the provisioning of virtual PCs, virtual workstations, and even virtualized compute on a single board.
SUPERIOR STREAMING MEDIA PERFORMANCE
The NVIDIA A16 features the highest number of video encoders and decoders with four on-chip hardware encoders (NVENC) and eight decoder (NVDEC) units in a single A16 board. This provides the best encode, decode and transcode performance translating to a maximized number of video streams per A16 board at an attractive price point versus alternative offerings.

NVIDIA A16 Datasheet

NVIDIA A16 Brief