NVIDIA GeForce RTX 4070 Ti vs NVIDIA Rubin GPU
GPU Specs Compare
Graphics Card
Release Date
Jan 2023
Jan 2026
Generation
GeForce 40
Server Rubin
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
2310 MHz
700 MHz
Boost Clock
2610 MHz
2267 MHz
Memory Clock
1313 MHz
2695 MHz
Memory
Memory Size
12GB
288GB
Memory Type
GDDR6X
HBM4
Memory Bus
192bit
16384bit
Bandwidth
504.2GB/s
22.1TB/s
Render Config
SM Count
60
224
Shading Units
7680
28672
TMUs
240
896
ROPs
80
24
Tensor Cores
240
896
RT Cores
60
-
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
48 MB
128 MB
Theoretical Performance
Pixel Rate
208.8 GPixel/s
54.41 GPixel/s
Texture Rate
626.4 GTexel/s
2031.2 GTexel/s
FP16 (half)
40.09 TFLOPS
260.0 TFLOPS
FP32 (float)
40.09 TFLOPS
130.0 TFLOPS
FP64 (double)
626.4 GFLOPS
32.50 TFLOPS
Graphics Processor
GPU Name
AD104
GR100
GPU Variant
AD104-400-A1
-
Architecture
Ada Lovelace
Rubin
Foundry
TSMC
TSMC
Process Size
4 nm
3 nm
Transistors
35.8 billion
336 billion
Die Size
295 mm²
1456 mm²
Board Design
TDP
285W
2300W
Suggested PSU
600 W
2700 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-pin
-
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.9
10.7
Shader Model
6.7
N/A