NVIDIA A16 - dense graphics VDI on a single board
The A16 is built around a solution unconventional for the data center: four independent Ampere GPUs on one board, 16 GB of GDDR6 with ECC each - 64 GB in total. This architecture allows up to 64 concurrent vPC users per card and mixing different vGPU profiles and workload types without allocating separate hardware for each scenario.
The card is designed for virtual desktop infrastructure: knowledge workers get native-PC-level responsiveness remotely, while entry-level virtual workstations for CAD/CAM run through RTX vWS with sufficient framebuffer per user. The full NVIDIA virtualization stack is supported - vPC, vApps, RTX vWS, AI Enterprise and vCS.
- 4 Ampere GPUs, 5120 CUDA cores (4x 1280), 160 3rd-gen Tensor cores, 40 2nd-gen RT cores
- 64 GB GDDR6 with ECC (4x 16 GB), 128-bit bus per GPU
- 4x NVENC + 8x NVDEC: H.265, VP9, AV1 decode for dense video transcoding
- PCI Express 4.0 x16, passive cooling, 8-pin EPS power, up to 250 W
- FHFL form factor, dual slot, no physical video outputs - output via vGPU
Thanks to four encoders and eight decoders, the A16 sustains a high density of video conferencing and streaming media, while idle VDI resources can be given over to AI inference through NVIDIA AI Enterprise. This is the retail version in PNY branded packaging with full warranty. ETE.UA is an official PNY/NVIDIA supplier in Ukraine; selection for your hypervisor and user profiles - phone +380 93,594 00 77.
Frequently Asked Questions
What power supply does this card need?
Auxiliary power connector: 1x8pin. With two of these cards in one system, size the supply with headroom and check the circuit rating.
Will this card fit my case?
The card takes 2 slots, length 267 mm. Measure the clearance from the rear panel to the drive cage before ordering: that is where a few millimetres usually go missing.
What model size fits into 64 GB of memory?
Roughly a 30B model at 4-bit or a 13B model at 8-bit. The exact figure depends on context length: longer conversations consume more cache. Memory: 64 GB GDDR6.
Which GPU does this card use?
NVIDIA A16, 5120 compute cores. The GPU generation decides which compute formats are accelerated in hardware, and that affects inference speed more than raw memory capacity does.
What warranty is provided and what is in the box?
Warranty: 36 months. Ships in the manufacturer's original packaging. In the box: 1x 8-pin CPU power cable.
Not sure this card fits your system?
We will check compatibility with your platform, calculate the power draw for your configuration and tell you whether the memory is enough for your models.
The model you need is out of stock? ETE is listed among official PNY partners, so we bring professional NVIDIA cards to order with the manufacturer warranty.
Message us on Telegram or leave a request.
