NVIDIA Rubin Ultra GPU vs NVIDIA RTX 6000 Ada Generation

GPU Specs Compare

Graphics Card

Release Date
Jan 2027
Dec 2022
Generation
Server Rubin
Quadro Ada
Type
Desktop
Desktop
Bus Interface
PCIe 6.0 x16
PCIe 4.0 x16

Clock Speeds

Base Clock
700 MHz
915 MHz
Boost Clock
2267 MHz
2505 MHz
Memory Clock
1900 MHz
2500 MHz

Memory

Memory Size
1024GB
48GB
Memory Type
HBM4e
GDDR6
Memory Bus
32768bit
384bit
Bandwidth
31.1TB/s
960.0GB/s

Render Config

SM Count
448
142
Shading Units
57344
18176
TMUs
1792
568
ROPs
24
192
Tensor Cores
1792
568
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
128 MB
96 MB
RT Cores
-
142

Theoretical Performance

Pixel Rate
54.41 GPixel/s
481.0 GPixel/s
Texture Rate
4062.5 GTexel/s
1423 GTexel/s
FP16 (half)
520.0 TFLOPS
91.06 TFLOPS
FP32 (float)
260.0 TFLOPS
91.06 TFLOPS
FP64 (double)
65.00 TFLOPS
1423 GFLOPS

Graphics Processor

GPU Name
GR110
AD102
Architecture
Rubin Ultra
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
3 nm
5 nm
Transistors
670 billion
76.3 billion
Die Size
2912 mm²
609 mm²
GPU Variant
-
AD102

Board Design

TDP
3600W
300W
Suggested PSU
4000 W
700 W
Outputs
No outputs
4x DisplayPort 1.4a
Power Connectors
-
1x 16-pin

Graphics Features

DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
CUDA
10.7
8.9
Shader Model
N/A
6.8

📊 Benchmark

OctaneBench
-
1,068
Blender
-
11,394