NVIDIA Quadro and Quadro RTX GPUs

Key takeaways

  • 94 listings match this collection right now.
  • The larger Quadro RTX cards draw power through an 8-pin PCIe connector and occupy two expansion slots, so both power delivery and physical slot clearance need checking against the host.
  • An NVLink bridge pools memory across a matched pair, taking 24GB RTX 6000 cards to 48GB combined and 48GB RTX 8000 cards to 96GB combined.
  • The same above-4G-decoding and large-BAR firmware settings a datacenter card needs also apply when a Quadro RTX card is used for compute rather than for display output.

Quadro is the NVIDIA workstation line: certified drivers, ECC memory on the larger cards, and DisplayPort outputs. Quadro RTX cards (Turing) add ray-tracing and tensor cores and, at 24GB to 48GB, double as budget inference cards in workstations and tower servers with active cooling.

94 listings in this collection, filtered from Graphics Cards. The part number and manufacturer are stated on every listing, and the condition wherever the catalogue records one. For quantity, request a volume quote.

Items 1-12 of 94

Views:

How to choose gpus and accelerators

Datacenter cards (Tesla, A-series) are passively cooled and expect server airflow; workstation cards (Quadro, RTX A) carry their own fans and display outputs. Match the slot (PCIe generation and width), the auxiliary power the card needs, and the memory the workload needs: inference and video work fits in 16 GB to 24 GB, training and large models want 32 GB to 80 GB.

Other gpus and accelerators collections

Browse every collection by specification