With the NVIDIA A16, you can take remote work to the next level. It enables virtual desktops and workstations with the power and performance to tackle any project from anywhere when used with NVIDIA Virtual PC (vPC) or NVIDIA RTX Virtual Workstation (vWS) software. The NVIDIA Ampere architecture, designed specifically for high-density, graphics-rich virtual desktop infrastructure (VDI), allows A16 to provide twice the user density of the previous generation while ensuring the best possible user experience.
Designed for VDI Acceleration
Optimized for user density and, when used in conjunction with NVIDIA vPC software, allows for the creation of graphics-rich virtual PCs that can be accessed from anywhere.
Virtual Workstations at an Affordable Price
With NVIDIA RTX vWS software, entry-level virtual workstations with a large frame buffer per user can run workloads like computer-aided design (CAD).
Support a variety of user types with ease
On a single board, a unique quad-GPU board design allows the provisioning of mixed user profile sizes and user types, such as virtual PCs and virtual workstations.
Superior User Experience
Superior User Experience Provides higher frame rates and lower end-user latency than CPU-only VDI, resulting in more responsive applications and a user experience that is indistinguishable from that of a native PC.
Double the User Density
Designed specifically for graphics-intensive VDI, the board supports up to 64 concurrent users in a dual-slot form factor.
Display with High Resolution
Supports multiple high-resolution monitors (up to two 4K or a single 5K) in a virtualization environment for maximum productivity and photorealistic quality.
Encoder Throughput Increased by More Than 2x
More than double the encoder throughput compared to the previous generation M10, ensuring multiuser performance for streaming video and multimedia.
Video of the Highest Quality
Supports the latest codecs for the best video quality, including H.265 encode/decode, VP9, and AV1 decode.
PCI Express Gen 4
PCI Express Gen 4 data-transfer speeds from CPU memory are supported for data-intensive tasks.
Ampere Architecture by NVIDIA
Includes NVIDIA Ampere architecture-based CUDA cores, second-generation RT Cores, and third-generation Tensor Cores, allowing you to run compute workloads on unused VDI resources or host virtual workstations powered by NVIDIA RTX Virtual Workstation (vWS) software.
|GPU Memory||4x 16GB GDDR6 with error-correcting code (ECC)|
|GPU Memory Bandwidth||4x 200 GB/s|
|Max power consumption||250W|
|Interconnect||PCI Express Gen 4 x16|
|Form factor||Full height, full length (FHFL) dual slot|
|vGPU Software Support||NVIDIA Virtual PC (vPC), NVIDIA Virtual Applications (vApps), NVIDIA RTX Virtual Workstation (vWS), NVIDIA Virtual Compute Server (vCS), and NVIDIA AI Enterprise|
|NVENC | NVDEC||4x | 8x (includes AV1 decode)|
|NEBS Ready||Level 3|
|Power Connector||8-pin CPU|