Nvidia professional users rejoice; the Quadro RTX 6000 has gone up for pre-order on Nvidia's website for $6,300 a piece. But you better hurry up, as stock is limited to five per customer.
Introduced to the hardware world last August, the Quadro RTX 6000 is Nvidia's mid-level Turing-based Quadro model for tackling professional workflows, such as content creation in the video and film industry, automotive and architectural design and scientific visualization. The Quadro RTX 6000 is built around the full-fledged TU102 silicon, taking up 754-square-millimeters of space. Its large die is produced inside TSMC’s 12nm FinFET oven and contains 18.6 billion transistors. Additionally, the Quadro RTX 6000 comes equipped with 4,608 CUDA cores, 576 Tensor cores for AI and 72 RT cores for ray tracing activities. The graphics card also has 24GB of GDDR6 memory across a 384-bit memory interface. Unfortunately, Nvidia didn't reveal details on the Quadro RTX 6000's core or boost clocks.
The Quadro RTX 6000 posts strong performance on paper. According to Nvidia, the graphics card pumps out 16.3 TFLOPS of single precision (FP32) and 32.6 TFLOPS of half precision (FP16) performance. It is also capable of delivering up to 10 GigaRays/sec of ray tracing performance, 84 Tera RTX-OPS and 130.5 Tensor TFLOPS.
On the aesthetics side, the Quadro RTX 6000 features a traditional blower design. It measures 11.176 x 26.67cm and occupies two PCI slots. The graphics card has a maximum power consumption of 295W and draws its power from a PCIe 3.0 x16 slot and a pair of 8-pin PCIe power connectors. The Quadro RTX 6000 sports Nvidia's NVLink connector. Therefore, consumers can pair two of these bad boys together with a Quadro RTX NVLink HB Bridge to scale memory capacity to 48GB and drive bandwidth up to 100GB/s.
As for display connectors, the Quadro RTX 6000 is equipped with four DisplayPort 1.4 outputs and a USB Type-C port for Nvidia VirtualLink. The graphics card is priced at $6,300, and interested consumers can pre-order it directly from Nvidia.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Zhiye Liu is a news editor, memory reviewer, and SSD tester at Tom’s Hardware. Although he loves everything that’s hardware, he has a soft spot for CPUs, GPUs, and RAM.
-
Hetzbh Yeah, go buy an RTX 2080 with double the RAM (and it's ECC), lowered clock (see the cooling solution) at X6.5 the price, run! :)Reply -
KD_Gaming @hetzbh, are you dumb? Did you even read past the article title? These far outperform a regular card in workstation programs.Reply -
kinggremlin Reply21366764 said:@hetzbh, are you dumb? Did you even read past the article title? These far outperform a regular card in workstation programs.
Your first question was answered when he noted 8 times two is 24. Also, the RTX 6000 uses the same core as the 2080Ti, not the 2080. Even accounting for that mistake, 11 times 2 is still not 24.
Unlike the old days, I don't think this will outperform the 2080ti by much as the 2080ti isn't artificially crippled. You're paying for more RAM and certified drivers which are required by many enterprise software packages. -
kyotokid ...if you are into creating3D content and rendering large scenes, the 6000 will defintiely out perform the 2080 Ti. That 24 GB (which with a second card and NVLink becomes 48) over the Ti's 11 GB is a major benefit. Also Quadro drivers are optimised for CG production rather than gaming.Reply
You likely won't see full memory pooling in the consumer RTX cards either as NVLInk there only acts as a "beefed up" version of SLI. Also as I recently read, Iray will not take advantage of the RTX cores as Optex Prime (which is needed) is not enabled.
For less than the cost of a single RTX6000 you can get two RTX5000s with NVLInk and have 32 GB of VRAM which is a heck of a lot for most 3D artist's purposes. -
pokeman If the ram are slower why use the 6000 for the raytrace showcase of the rtx turing annoucement on tomb raider?Reply -
pokeman But they must have deemed it faster than a 2080ti even in gaming (albeit for raytracing loads).Reply