GeForce RTX 3080 Ti vs GeForce GTX 1050 Ti
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3080 Ti and 4GB VRAM GeForce GTX 1050 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3080 Ti 's Advantages
Released 4 years and 7 months late
Boost Clock has increased by 20% (1665MHz vs 1392MHz)
More VRAM (12GB vs 4GB)
Larger VRAM bandwidth (912.4GB/s vs 112.1GB/s)
9472 additional rendering cores
GeForce GTX 1050 Ti 's Advantages
Lower TDP (75W vs 350W)
Score
Benchmark
FP32 (float)
GeForce RTX 3080 Ti
+1494%
34100
GeForce GTX 1050 Ti
2138
3DMark Time Spy
GeForce RTX 3080 Ti
+734%
19629
GeForce GTX 1050 Ti
2353
3DMark Time Spy Extreme
GeForce RTX 3080 Ti
+817%
10032
GeForce GTX 1050 Ti
1093
Shadow of the Tomb Raider 2160p
GeForce RTX 3080 Ti
+736%
92
GeForce GTX 1050 Ti
11
Shadow of the Tomb Raider 1440p
GeForce RTX 3080 Ti
+665%
153
GeForce GTX 1050 Ti
20
Shadow of the Tomb Raider 1080p
GeForce RTX 3080 Ti
+610%
199
GeForce GTX 1050 Ti
28
Battlefield 5 2160p
GeForce RTX 3080 Ti
+570%
114
GeForce GTX 1050 Ti
17
Battlefield 5 1440p
GeForce RTX 3080 Ti
+450%
187
GeForce GTX 1050 Ti
34
Battlefield 5 1080p
GeForce RTX 3080 Ti
+314%
199
GeForce GTX 1050 Ti
48
GTA 5 1080p
GeForce RTX 3080 Ti
+5%
186
GeForce GTX 1050 Ti
176
Graphics Card
May 2021
Release Date
Oct 2016
GeForce 30
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1365 MHz
Base Clock
1291 MHz
1665 MHz
Boost Clock
1392 MHz
1188 MHz
Memory Clock
1752 MHz
Memory
12GB
Memory Size
4GB
GDDR6X
Memory Type
GDDR5
384bit
Memory Bus
128bit
912.4GB/s
Bandwidth
112.1GB/s
Render Config
80
SM Count
6
10240
Shading Units
768
320
TMUs
48
112
ROPs
32
320
Tensor Cores
-
80
RT Cores
-
128 KB (per SM)
L1 Cache
48 KB (per SM)
6 MB
L2 Cache
1024 KB
Theoretical Performance
186.5 GPixel/s
Pixel Rate
44.54 GPixel/s
532.8 GTexel/s
Texture Rate
66.82 GTexel/s
34.10 TFLOPS
FP16 (half)
33.41 GFLOPS
34.10 TFLOPS
FP32 (float)
2.138 TFLOPS
532.8 GFLOPS
FP64 (double)
66.82 GFLOPS
Board Design
350W
TDP
75W
750 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
1x 12-pin
Power Connectors
None
Graphics Processor
GA102
GPU Name
GP107
GA102-225-A1
GPU Variant
GP107-400-A1
Ampere
Architecture
Pascal
Samsung
Foundry
Samsung
8 nm
Process Size
14 nm
28.3 billion
Transistors
3.3 billion
628 mm²
Die Size
132 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
6.1
6.6
Shader Model
6.4
