
AMD
AMD Radeon PRO W7900 48GB
RDNA 3 professional workstation card with 48 GB GDDR6 ECC and DisplayPort 2.1 for CAD, DCC and visualization.
| Dostępność | W magazynie |
|---|---|
| SKU | AXL-GPU-W7900 |
| Minimalne zamówienie | 1 unit |
| Stan | Nowy |
| Ceny | Na zapytanie |
Opis
The Radeon PRO W7900 is the flagship of the AMD RDNA 3 professional line, with 48 GB of ECC GDDR6 on a 384-bit interface. It targets CAD and BIM, product design, media and entertainment pipelines, colour-critical review and multi-display visualization, and its DisplayPort 2.1 outputs drive high-resolution, high-refresh panel setups that older connectors cannot. Allow for the triple-slot cooler on the standard card when planning multi-GPU towers; a dual-slot version is offered where slot space is tight.
AXISLINK supplies the W7900 through professional-graphics distribution, with the board variant and serial number written on the quotation so a studio can standardise on one part. Cards ship on their own or inside a workstation we assemble and test with the certified driver package installed. Export documentation and freight from Hong Kong form part of the order.
Specyfikacja
| Architecture | AMD RDNA 3 |
|---|---|
| Memory | 48 GB GDDR6 with ECC, 384-bit |
| Memory bandwidth | 864 GB/s |
| Compute units | 96 |
| Form factor | PCIe 4.0 x16, triple-slot active cooling; a dual-slot variant is also produced |
|---|---|
| Display outputs | 3x DisplayPort 2.1 and 1x Mini DisplayPort 2.1 |
| Total board power | 295 W |
|---|
Zapytaj o wycenę
Wycena dla AMD Radeon PRO W7900 48GB. Odpowiadamy formalną fakturą proforma, zwykle w ciągu 24 godzin.
Więcej w kategorii Karty GPU i akceleratory
Zobacz kategorię
NVIDIA
NVIDIA H200 141GB SXM
Hopper SXM module with 141 GB HBM3e for large-model training and memory-bound inference on HGX baseboards.

NVIDIA
NVIDIA L40S 48GB
Ada Lovelace data-center card with 48 GB GDDR6 ECC for inference, fine-tuning, rendering and virtual workstations.

NVIDIA
NVIDIA H100 80GB
Hopper-architecture data-center GPU for large-scale AI training and inference. PCIe and SXM variants.