NVIDIA A16 64GB in OEM supply for server integrations
This SKU is supplied as OEM (tray, factory packaging) - a solution for system integrators and server builders who do not need a retail box and bundle. The official manufacturer warranty is retained, while ECC memory and enterprise drivers deliver the same production stability as the retail variant.
Technically this is a full A16: four independent Ampere GPUs on one board with 16 GB GDDR6 and ECC each, 64 GB in total. The card is designed for high-density graphics VDI - up to 64 concurrent vPC users per board, twice the density of its M10 predecessor and a lower TCO per seat. Mixed vGPU profiles on a single card make it possible to serve both simple knowledge workers and entry-level workstations for CAD via RTX vWS.
- 5120 CUDA cores (4x 1280), 160 3rd-gen Tensor, 40 2nd-gen RT
- 64 GB GDDR6 ECC (4x 16 GB), 128-bit per GPU, PCI Express 4.0 x16
- 4x NVENC + 8x NVDEC with H.265, VP9 and AV1 decode
- Passive cooling for server airflow, 8-pin EPS power, up to 250 W
- FHFL, dual slot, optional Secure/Measured Boot with hardware root of trust
The whole NVIDIA vGPU stack is supported: vPC, vApps, RTX vWS, AI Enterprise and vCS, so free VDI resources can be directed to AI inference. ETE.UA supplies the A16 on B2B terms - invoice with VAT, bank transfer, calculation of the number of cards for your user density. Check availability status by 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. 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.
