NVIDIA RTX 6000 Ada Workstation Graphics Card With Over 18K Cores & 48 GB Memory Hits Retail For $6800 US

Hassan Mujtaba

Today, NVIDIA announces the retail availability of its flagship workstation graphics card based on the Ada architecture, the RTX 6000 Ada.

NVIDIA's RTX 6000 Workstation Graphics Card Features A Whopping 18K+ Cores, and 48 GB Memory, All For A Price of $6800 US

The NVIDIA RTX 6000 graphics card is aimed at the workstation segment and will utilize the Pro driver suite. It is not intended to be used for gaming though one can still game on it if they want since NVIDIA's drivers are very flexible. One might easily get confused with the naming scheme of the new card but one should remember that the Ampere generation had an 'A' at the beginning of the model name whereas the Ada generation doesn't feature any alphabets in the beginning. The card is simply called the RTX 6000 instead of the RTX A6000 (Last-gen).

Related StoryHassan Mujtaba
NVIDIA GeForce RTX 4090 Ti Allegedly Features Ada GPU With 18176 Cores, 24 GB GDDR6X Memory, 600W TBP

The specifications of the NVIDIA RTX 6000 are also better than the GeForce RTX 4090. It has just 2 SMs disabled at 142 which offer up to 18,176 CUDA cores. That's 11% more cores & SMs than the RTX 4090 GPU. But NVIDIA surely has some room left for an even higher-end variant that will use those 2 remaining SM units. The card comes with a similar boost clock of 2.5 GHz and has double the VRAM capacity at 48 GB (EEC) versus the 24 GB featured on the RTX 4090. The card does use slower 20 Gbps GDDR6X memory dies versus the 21 Gbps dies featured on the gaming graphics card.

Architecture NVIDIA Ada Lovelace Architecture
Process Size 4nm NVIDIA Custom Process | TSMC
Die Size 608.4 mm
Transistors 76.3 Billion
CUDA Cores 18176
Tensor Cores 568 Gen-4
RT Cores 142 Gen-3
GPU Memory 48 GB GDDR6 with ECC
Memory Interface 384-bit
Graphics Bus PCI Express Gen 4.0 x16
Display Connectors DP 1.4 (4)
Form Factor 4.4" H x 10.5" L, Dual-Slot
Thermal Solution Active Fansink
AR/MR/VR/XR Capable Yes
NVIDIA 3D Vision and 3D Vision Pro Support via Optional 3-pin mini-DIN
Frame Lock Compatible with NVIDIA Quadro Sync II
Maximum Power Consumption 300 W
Auxiliary Power Connector 1x PCIe CEMS 16-pin
NVENC | NVDEC 3x | 3x + AV1 Encode and Decode

As for performance, the NVIDIA RTX 6000 'Ada' graphics card offers 91.1 TFLOPs of FP32, 210.6 TFLOPs of RT, and 1457 TFLOPs of Tensor core performance. While the RTX 4090 requires 450W TBP, the RTX 6000 is rated at just 300W, making it quite the efficiency powerhouse. But all of that extra prowess and workstation goodness comes at a cost.

The NVIDIA RTX 6000 Ada is now available through NVIDIA and its partners for a price of $6800 US which is also its official MSRP. That's almost 50% higher than the RTX A6000, its Ampere GPU-based predecessor, and 4.25x higher than the RTX 4090's MSRP. The price may be entirely worth it as this card has workstation capabilities and performance that are second to none. Ada has some insane compute capabilities and a lot of creation/AI prowess under its hood and with proper workstation drivers, this beast would fly.

NVIDIA Workstation Graphics Card Lineup:

Graphics CardRTX 6000RTX A6000Quadro RTX 8000Quadro RTX 6000Quadro GV100
GPUAda Lovelace GPUAmpere GPUTuring GPUTuring GPUVolta GPU
GPU Process5nm8nm12nm12nm12nm
Die Size608mm2628mm²754mm²754mm²815mm²
GPU Cores18176 Cores10752 Cores4608 Cores4608 Cores5120 Cores
Tensor Cores568 Cores656 Cores576 Cores576 Cores640 Cores
Boost Clock2.50 GHz1.80 GHz1.77 GHz1.77 GHz1.62 GHz
Single Precision91.1 TFLOPs38.7 TFLOPs16.31 TFLOPs16.31 TFLOPs16.66 TFLOPs
Ray Tracing Spec210.6 TFLOPs75.4 TFLOPs10 GigaRays/Sec10 GigaRays/SecN/A
Memory Bus384-bit384-bit384-bit384-bit4096-bit
Memory Bandwidth960 GB/s768 GB/s672 GB/s672 GB/s870 GB/s
Launch Price$6800 US$4650 US$10000 US$6300 US$9000 US
Launch DateQ1 2023Q4 2020Q4 2018Q4 20182018
Share this story

Deal of the Day