NVIDIA GeForce RTX 3070 Ti vs NVIDIA Rubin GPU
GPU Specs Compare
Graphics Card
Release Date
May 2021
Jan 2026
Generation
GeForce 30
Server Rubin
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
1575 MHz
700 MHz
Boost Clock
1770 MHz
2267 MHz
Memory Clock
1188 MHz
2695 MHz
Memory
Memory Size
8GB
288GB
Memory Type
GDDR6X
HBM4
Memory Bus
256bit
16384bit
Bandwidth
608.3GB/s
22.1TB/s
Render Config
SM Count
48
224
Shading Units
6144
28672
TMUs
192
896
ROPs
96
24
Tensor Cores
192
896
RT Cores
48
-
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
4 MB
128 MB
Theoretical Performance
Pixel Rate
169.9 GPixel/s
54.41 GPixel/s
Texture Rate
339.8 GTexel/s
2031.2 GTexel/s
FP16 (half)
21.75 TFLOPS
260.0 TFLOPS
FP32 (float)
21.75 TFLOPS
130.0 TFLOPS
FP64 (double)
339.8 GFLOPS
32.50 TFLOPS
Graphics Processor
GPU Name
GA104
GR100
GPU Variant
GA104-400-A1
-
Architecture
Ampere
Rubin
Foundry
Samsung
TSMC
Process Size
8 nm
3 nm
Transistors
17.4 billion
336 billion
Die Size
392 mm²
1456 mm²
Board Design
TDP
290W
2300W
Suggested PSU
600 W
2700 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
No outputs
Power Connectors
1x 12-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
8.6
10.7
Shader Model
6.6
N/A
📊 Benchmark
3DMark Time Spy
14,872
-
3DMark Time Spy Extreme
7,416
-
3DMark Speed Way
3,761
-