NVIDIA GeForce RTX 2080 Ti 12 GB vs NVIDIA GeForce RTX 3070 Ti 16 GB
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 2080 Ti 12 GB and 16GB VRAM GeForce RTX 3070 Ti 16 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 2080 Ti 12 GB 's Advantages
Larger VRAM bandwidth (768.0GB/s vs 608.3GB/s)
Lower TDP (250W vs 290W)
NVIDIA GeForce RTX 3070 Ti 16 GB 's Advantages
Boost Clock has increased by 8% (1770MHz vs 1635MHz)
More VRAM (16GB vs 12GB)
1536 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 2080 Ti 12 GB
15.07 TFLOPS
GeForce RTX 3070 Ti 16 GB
+44%
21.75 TFLOPS
3DMark Time Spy
GeForce RTX 2080 Ti 12 GB
14622
GeForce RTX 3070 Ti 16 GB
+1%
14872
3DMark Time Spy Extreme
GeForce RTX 2080 Ti 12 GB
7001
GeForce RTX 3070 Ti 16 GB
+5%
7416
3DMark Speed Way
GeForce RTX 2080 Ti 12 GB
3042
GeForce RTX 3070 Ti 16 GB
+23%
3761
Blender
GeForce RTX 2080 Ti 12 GB
3378
GeForce RTX 3070 Ti 16 GB
+21%
4092
OctaneBench
GeForce RTX 2080 Ti 12 GB
253
GeForce RTX 3070 Ti 16 GB
+56%
397
Graphics Card
Unknown
Release Date
Unknown
GeForce 20
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1350 MHz
Base Clock
1575 MHz
1635 MHz
Boost Clock
1770 MHz
2000 MHz
Memory Clock
1188 MHz
Memory
12GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6X
384bit
Memory Bus
256bit
768.0GB/s
Bandwidth
608.3GB/s
Render Config
-
-
-
72
SM Count
48
4608
Shading Units
6144
288
TMUs
192
96
ROPs
96
576
Tensor Cores
192
72
RT Cores
48
64 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
157.0 GPixel/s
Pixel Rate
169.9 GPixel/s
470.9 GTexel/s
Texture Rate
339.8 GTexel/s
30.14 TFLOPS
FP16 (half)
21.75 TFLOPS
15.07 TFLOPS
FP32 (float)
21.75 TFLOPS
470.9 GFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
250W
TDP
290W
600 W
Suggested PSU
600 W
1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 12-pin
Graphics Processor
TU102
GPU Name
GA104
TU102-350-A1
GPU Variant
GA104-401-A1
Turing
Architecture
Ampere
TSMC
Foundry
Samsung
12 nm
Process Size
8 nm
18.6 billion
Transistors
17.4 billion
754 mm²
Die Size
392 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
1.3
7.5
CUDA
8.6
6.8
Shader Model
6.6
