We take cryptocurrency — so the coins you hold can buy real hardware.Pay in crypto, spend it on real hardware. Free insured shipping worldwide over $399. Plain, unbranded boxes, sent from Germany.Free insured shipping over $399. Your rate is locked for 30 minutes once checkout opens.Rate locked 30 minutes. Every item sealed, serial-checked and covered by a 24-month warranty.Sealed, 24-month warranty.

Saved items Sign in
Compact SFF graphics card in matte black finish, single-slot bracket with blower-style cooler and PCIe 4.0 edge connector

PNY Technologies, Inc.

PNY Technologies, Inc. VCNRTX4000ADALP-SB RTX 4000 SFF Ada 20GB workstation graphics card

SKU CH-QP1Y-1XPXZ

Workstation GPU with 6144 CUDA cores, 192 Tensor Cores, 48 RT cores and 20GB GDDR6 ECC memory at 280 GB/s in a 70W SFF design

  • Memory TypeComputer Accessories
  • Ada Lovelace architecture powers professional workloads with 6,144 CUDA cores
  • 192 Tensor cores accelerate AI and deep-learning tasks
  • 48 RT cores enable real-time rendering for visualisation
  • 20 GB GDDR6 memory with ECC supports large datasets
  • 70 W maximum power draw fits small-form-factor workstations

Compact workstation GPU for professional

The PNY RTX 4000 SFF Ada packs 6144 CUDA cores and 20GB GDDR6 memory into a small-form-factor design. It targets engineers and creators who need certified application performance inside space-constrained workstations. The 70W maximum power draw keeps thermal demands modest for dense builds.

Single-slot PCI-E 4.0 installation with 70W envelope

The card plugs into a standard PCI-E 4.0 x16 slot and draws all power from the slot itself, so no external connectors are required. Builders must verify that the chassis can accommodate a full-height, single-slot card and that the motherboard firmware supports PCI-E 4.0 signalling. Airflow restrictions in tight enclosures are the most common cause of thermal throttling.

280 GB/s bandwidth caps sustained compute throughput

The 280 GB/s memory interface feeds 192 Tensor Cores and 48 RT cores, but bandwidth becomes the limiting factor for large dataset streaming. Workloads that exceed the 20GB frame buffer will spill to system memory across the PCI-E 4.0 bus, adding latency. Buyers needing more VRAM or multi-GPU scaling should consider larger form-factor alternatives.

Highlights

  • Ada Lovelace architecture powers professional workloads with 6,144 CUDA cores
  • 192 Tensor cores accelerate AI and deep-learning tasks
  • 48 RT cores enable real-time rendering for visualisation
  • 20 GB GDDR6 memory with ECC supports large datasets
  • 70 W maximum power draw fits small-form-factor workstations

Specifications

BrandPNY
ModelVCNRTX4000ADALP-SB
Memory TypeComputer Accessories

Questions about this item

How can I confirm the RTX 4000 SFF Ada is running correctly after installation?

Verify the GPU appears in Device Manager with 20GB GDDR6 memory and 6,144 CUDA cores, then run a short workload to ensure the 70W power draw is stable.

What comes in the box with the VCNRTX4000ADALP-SB and what must I source separately?

The card ships in a small box; you will need a PCI-E 4.0 x16 slot and a power supply capable of delivering 70W for the graphics bus.

Which version of the RTX 4000 SFF Ada should I choose for my workload?

This model provides 20GB GDDR6 with ECC, 280 GB/s bandwidth, 192 Tensor Cores and 48 RT cores — suited for professional visualization and compute tasks.

Also in this aisle

People compared these

Same shelf, same checkout — eight coins and a 30-minute rate lock.