GeForce RTX 5090 vs GeForce RTX 3070 Ti 8 GB GA102
We compared two Desktop platform GPUs: 32GB VRAM GeForce RTX 5090 and 8GB VRAM GeForce RTX 3070 Ti 8 GB GA102 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5090 Advantages
Released 2 years and 3 months late
Boost Clock has increased by 36% (2407MHz vs 1770MHz)
More VRAM (32GB vs 8GB)
Larger VRAM bandwidth (1.79TB/s vs 608.3GB/s)
15616 additional rendering cores
GeForce RTX 3070 Ti 8 GB GA102 Advantages
Lower TDP (290W vs 575W)
Score
Benchmark
FP32 (float)
GeForce RTX 5090
+381%
104800
GeForce RTX 3070 Ti 8 GB GA102
21750
Graphics Card
Jan 2025
Release Date
Oct 2022
GeForce 50
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
2017 MHz
Base Clock
1575 MHz
2407 MHz
Boost Clock
1770 MHz
1750 MHz
Memory Clock
1188 MHz
Memory
32GB
Memory Size
8GB
GDDR7
Memory Type
GDDR6X
512bit
Memory Bus
256bit
1.79TB/s
Bandwidth
608.3GB/s
Render Config
170
SM Count
48
21760
Shading Units
6144
680
TMUs
192
176
ROPs
96
680
Tensor Cores
192
170
RT Cores
48
128 KB (per SM)
L1 Cache
128 KB (per SM)
96 MB
L2 Cache
4 MB
Theoretical Performance
423.6 GPixel/s
Pixel Rate
169.9 GPixel/s
1637 GTexel/s
Texture Rate
339.8 GTexel/s
104.8 TFLOPS
FP16 (half)
21.75 TFLOPS
104.8 TFLOPS
FP32 (float)
21.75 TFLOPS
1.637 TFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
575W
TDP
290W
950 W
Suggested PSU
600 W
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 12-pin
Graphics Processor
GB202
GPU Name
GA102
GB202-300-A1
GPU Variant
GA102-150-A1
Blackwell 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
92.2 billion
Transistors
28.3 billion
750 mm²
Die Size
628 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.3
12.0
CUDA
8.6
6.8
Shader Model
6.6
