在此之前，NVIDIA的专业显卡通常以“RTX+四位数字+架构简称”的方式命名，例如RTX 6000 ADA。而此次新加入的“PRO”字样，让这款显卡的名字更加贴合其专业定位，类似于AMD的Radeon PRO系列。 从外观设计来看，RTX PRO 6000融合了RTX 50系和RTX 40系公版显卡的特点。

相比上一代RTX 6000 Ada显卡，CUDA核心数量提升了32%，而显存容量更是实现了翻倍增长。此外，这款显卡的功耗也有了显著提升，其TGP达到了600W，这一功耗水平可能是NVIDIA工作站显卡历史上首次超越游戏显卡。 散热设计方面，RTX PRO 6000 Blackwell依然采用了双风扇方案 ...

TL;DR: NVIDIA's RTX PRO 6000 Blackwell workstation GPU series will debut at GTC 2025, featuring the GB202 GPU with 24064 CUDA cores, 96GB of GDDR7 memory, and a 600W TDP. It includes 752 Tensor ...

for a 26% increase over last generation's RTX 6000 Ada. Nvidia offers this GPU in Workstation, Workstation Max-Q, and Server editions; the Max-Q's TGP is capped at 300W, while the server variant ...

They include 24,064 CUDA cores, 752 Tensor cores, and 188 RT cores. For comparison, NVIDIA's RTX 6000 Ada card based on Ada Lovelace features 18,176 CUDA cores, 568 Tensor cores, and 142 RT cores.

Arguably the most reliable GPU info leaker of them all, Kopite7kimi, has dropped a load of specs for Nvidia's upcoming RTX 5050 ... higher than a lowest-spec Ada laptop chip, but the performance ...