Nvidia has quietly started selling its RTX 6000 Ada Generation graphics cards. Based on his AD102 GPU with 18,176 CUDA cores enabled, this is the “fattest” AD102 configuration currently available. 142 of the 144 streaming multiprocessors are enabled. With a power consumption rating of 300W, this board is designed for computer-aided design, digital content creation, virtual desktop infrastructure, and other professional applications.
Prices vary considerably, ranging from $6,800 to $8,600 depending on the retailer. Nvidia’s card listed for $6,800 (opens in new tab), limited to 5 per customer — in case you’re trying to put together a large number of workstations.other Outlets like CDW (opens in new tab) We have also increased the price by about 25% and are set to be available in 4-6 weeks.
Nvidia’s RTX 6000 Ada, based on the AD102 GPU, has 18,176 CUDA cores enabled, and Nvidia doesn’t specify clocks anywhere, but PNY (opens in new tab) When lead tech (opens in new tab) It quotes a computing performance of 91.1 FP32 TFLOPS. This equates to a GPU boost clock of 2505 MHz, about 10% higher than his GeForce RTX 4090 which has 16,384 CUDA cores. However, there are distinct differences between the RTX 6000 Ada and his consumer-facing RTX 4090.
Designed for professional applications, the RTX 6000 Ada features 48 GB of GDDR6 memory with ECC and a peak memory bandwidth of 960 MB/s, slightly lower than the 1,008 MB/s offered by the GeForce RTX 4090 is equipped with This suggests Nvidia. uses 20 Gbps GDDR6 memory instead of the slightly faster 21 Gbps GDDR6X, but GDDR6 chips can also draw slightly lower power.
The RTX 6000 is equipped with four DisplayPort 1.4a connectors, capable of driving four 4K or 5K displays (4K @ 240 Hz supported via DSC), or two 8K displays (120 Hz with DSC).
One of the interesting things about the RTX 6000 Ada is its power consumption. Despite higher computing performance and 48GB of onboard memory, the RTX 6000 Ada is rated at just 300W, down from the 450W rating of the gamer-oriented GeForce RTX 4090. Both GPUs feature similar official boost clocks of around 2.5 GHz, but the RTX 6000 has a lower guaranteed minimum clock, and we don’t think it will clock that high for heavy compute workloads.
Due to its relatively limited power consumption, the RTX 6000 Ada Generation graphics cards come with dual-width cooling systems and blower fans to ensure they fit securely in workstations and servers. It uses a single 12VHPWR (16-pin CEM 5.0 PCIe) power connector for power delivery, so you’ll need a suitable cable adapter to fit existing machines that don’t have a native 16-pin connector.
Another interesting aspect of Nvidia’s RTX 6000 Ada professional graphics card is its price. Nvidia sells the board for $6,800, slightly less than the $6,999 launch price of its RTX A6000 predecessor. $8,615while Japanese retailers @momomo_us lists the units of $8,524 Excluding tax. I’m not sure why the reseller is charging more than his Nvidia itself, but for now it seems to make the most sense for him to buy the RTX 6000 Ada board directly from Nvidia. .