GeForce RTX 3080 vs GeForce RTX 5070
We compared two Desktop platform GPUs: 10GB VRAM GeForce RTX 3080 and 12GB VRAM GeForce RTX 5070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3080 Advantages
Larger VRAM bandwidth (760.3GB/s vs 672.0GB/s)
2560 additional rendering cores
GeForce RTX 5070 Advantages
Released 4 years and 6 months late
Boost Clock has increased by 47% (2512MHz vs 1710MHz)
More VRAM (12GB vs 10GB)
Lower TDP (250W vs 320W)
Score
Benchmark
FP32 (float)
GeForce RTX 3080
29770
GeForce RTX 5070
+3%
30870
3DMark Time Spy
GeForce RTX 3080
17662
GeForce RTX 5070
+27%
22544
3DMark Time Spy Extreme
GeForce RTX 3080
8879
GeForce RTX 5070
+21%
10789
3DMark Speed Way
GeForce RTX 3080
4633
GeForce RTX 5070
+27%
5896
Graphics Card
Sep 2020
Release Date
Mar 2025
GeForce 30
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1440 MHz
Base Clock
2325 MHz
1710 MHz
Boost Clock
2512 MHz
1188 MHz
Memory Clock
1750 MHz
Memory
10GB
Memory Size
12GB
GDDR6X
Memory Type
GDDR7
320bit
Memory Bus
192bit
760.3GB/s
Bandwidth
672.0GB/s
Render Config
68
SM Count
48
8704
Shading Units
6144
272
TMUs
192
96
ROPs
80
272
Tensor Cores
192
68
RT Cores
48
128 KB (per SM)
L1 Cache
128 KB (per SM)
5 MB
L2 Cache
48 MB
Theoretical Performance
164.2 GPixel/s
Pixel Rate
201.0 GPixel/s
465.1 GTexel/s
Texture Rate
482.3 GTexel/s
29.77 TFLOPS
FP16 (half)
30.87 TFLOPS
29.77 TFLOPS
FP32 (float)
30.87 TFLOPS
465.1 GFLOPS
FP64 (double)
482.3 GFLOPS
Board Design
320W
TDP
250W
700 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
1x 12-pin
Power Connectors
1x 16-pin
Graphics Processor
GA102
GPU Name
GB205
GA102-200-KD-A1
GPU Variant
GB205-300-A1
Ampere
Architecture
Blackwell 2.0
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
28.3 billion
Transistors
31.1 billion
628 mm²
Die Size
263 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
8.6
CUDA
10.1
6.6
Shader Model
6.8
