NVIDIA Rubin Ultra GPU vs NVIDIA GeForce RTX 3070 Ti Max Q

GPU Specs Compare

Graphics Card

Release Date
Jan 2027
Jan 2022
Generation
Server Rubin
GeForce 30 Mobile
Type
Desktop
Mobile
Bus Interface
PCIe 6.0 x16
PCIe 4.0 x16

Clock Speeds

Base Clock
700 MHz
510 MHz
Boost Clock
2267 MHz
1035 MHz
Memory Clock
1900 MHz
1500 MHz

Memory

Memory Size
1024GB
8GB
Memory Type
HBM4e
GDDR6
Memory Bus
32768bit
256bit
Bandwidth
31.1TB/s
384.0GB/s

Render Config

SM Count
448
46
Shading Units
57344
5888
TMUs
1792
184
ROPs
24
96
Tensor Cores
1792
184
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
128 MB
4 MB
RT Cores
-
46

Theoretical Performance

Pixel Rate
54.41 GPixel/s
99.36 GPixel/s
Texture Rate
4062.5 GTexel/s
190.4 GTexel/s
FP16 (half)
520.0 TFLOPS
12.19 TFLOPS
FP32 (float)
260.0 TFLOPS
12.19 TFLOPS
FP64 (double)
65.00 TFLOPS
190.4 GFLOPS

Graphics Processor

GPU Name
GR110
GA104
Architecture
Rubin Ultra
Ampere
Foundry
TSMC
Samsung
Process Size
3 nm
8 nm
Transistors
670 billion
17.4 billion
Die Size
2912 mm²
392 mm²

Board Design

TDP
3600W
80W
Suggested PSU
4000 W
-
Outputs
No outputs
No outputs
Power Connectors
-
None

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
8.6
Shader Model
N/A
6.6