NVIDIA GeForce RTX 3060 Ti GA103 vs NVIDIA GeForce RTX 3080 Ti 20 GB
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GA103 and 20GB VRAM GeForce RTX 3080 Ti 20 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3060 Ti GA103 's Advantages
Lower TDP (200W vs 350W)
NVIDIA GeForce RTX 3080 Ti 20 GB 's Advantages
More VRAM (20GB vs 8GB)
Larger VRAM bandwidth (760.3GB/s vs 448.0GB/s)
5376 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti GA103
16.2 TFLOPS
GeForce RTX 3080 Ti 20 GB
+110%
34.1 TFLOPS
3DMark Time Spy
GeForce RTX 3060 Ti GA103
11709
GeForce RTX 3080 Ti 20 GB
+64%
19216
3DMark Time Spy Extreme
GeForce RTX 3060 Ti GA103
5710
GeForce RTX 3080 Ti 20 GB
+70%
9720
3DMark Speed Way
GeForce RTX 3060 Ti GA103
2965
GeForce RTX 3080 Ti 20 GB
+66%
4926
Blender
GeForce RTX 3060 Ti GA103
3249
GeForce RTX 3080 Ti 20 GB
+83%
5956
OctaneBench
GeForce RTX 3060 Ti GA103
365
GeForce RTX 3080 Ti 20 GB
+75%
641
Graphics Card
Feb 2022
Release Date
Jan 2022
GeForce 30
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1410 MHz
Base Clock
1335 MHz
1665 MHz
Boost Clock
1665 MHz
1750 MHz
Memory Clock
1188 MHz
Memory
8GB
Memory Size
20GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
320bit
448.0GB/s
Bandwidth
760.3GB/s
Render Config
-
-
-
38
SM Count
80
4864
Shading Units
10240
152
TMUs
320
80
ROPs
112
152
Tensor Cores
320
38
RT Cores
80
128 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
133.2 GPixel/s
Pixel Rate
186.5 GPixel/s
253.1 GTexel/s
Texture Rate
532.8 GTexel/s
16.20 TFLOPS
FP16 (half)
34.10 TFLOPS
16.20 TFLOPS
FP32 (float)
34.10 TFLOPS
253.1 GFLOPS
FP64 (double)
532.8 GFLOPS
Board Design
200W
TDP
350W
550 W
Suggested PSU
750 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 12-pin
Power Connectors
1x 12-pin
Graphics Processor
GA103S
GPU Name
GA102
GA103-200-A1
GPU Variant
GA102-225-A1
Ampere
Architecture
Ampere
Samsung
Foundry
Samsung
8 nm
Process Size
8 nm
Unknown
Transistors
28.3 billion
496 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
1.3
Vulkan
1.3
8.6
CUDA
8.6
6.5
Shader Model
6.6
