PNY NVIDIA L40S 48GB OEM - an Ada Lovelace accelerator for server integrations
This SKU ships as OEM (tray, factory packaging) and is intended primarily for system integrators and for building rack servers in batches. The card is physically identical to the retail version: Ada Lovelace architecture, 18,176 CUDA cores, 568 4th-generation Tensor cores with Transformer Engine and 142 3rd-generation RT cores. FP8 performance reaches 733 TFLOPS (1,466 with sparsity), FP32 - 91.6 TFLOPS.
On board there are 48 GB of GDDR6 with ECC, a 384-bit bus and 864 GB/s of bandwidth. Passive cooling in a dual-slot FHFL form factor is designed for the directed airflow of a server chassis, TGP - 350 W, 16-pin power. The hardware NVENC/NVDEC blocks (3+3) with AV1 support cover video streaming and post-production.
- NVIDIA Ada Lovelace, 18,176 CUDA, 568 Tensor 4th gen
- 48 GB GDDR6 ECC, 384-bit, 864 GB/s
- FP8 Transformer Engine for LLM inference and training
- PCIe Gen4 x16, dual-slot, passive cooling, 350 W
- NVIDIA vGPU, Secure Boot with Root of Trust, NEBS Level 3
OEM (tray) supply does not reduce the official warranty - it is retained through the distributor. This is a rational choice for multi-card builds where branded retail packaging is not needed. B2B terms: VAT invoice, bank transfer payment, multi-GPU configuration calculation. Engineer consultation: +380 93,594 00 77.
Frequently Asked Questions
What power supply does this card need?
Auxiliary power connector: 1x16-pin. 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. 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 48 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: 48 GB GDDR6, 384 bit bus.
Which GPU does this card use?
NVIDIA L40S, 18176 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. Ask us to confirm the bundle contents before ordering.
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.
Read the review and measurements: NVIDIA L40S: one card for inference, rendering and VDI — review →
