Intel Arc A770 vs NVIDIA GeForce GTX 1660 Ti
We compared two Desktop platform GPUs: 16GB VRAM Arc A770 and 6GB VRAM GeForce GTX 1660 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Arc A770 's Advantages
Released 3 years and 8 months late
Boost Clock has increased by 36% (2400MHz vs 1770MHz)
More VRAM (16GB vs 6GB)
Larger VRAM bandwidth (512.0GB/s vs 288.0GB/s)
2560 additional rendering cores
NVIDIA GeForce GTX 1660 Ti 's Advantages
Lower TDP (120W vs 225W)
Score
Benchmark
FP32 (float)
Arc A770
+261%
19.66 TFLOPS
GeForce GTX 1660 Ti
5.437 TFLOPS
3DMark Time Spy
Arc A770
+113%
13560
GeForce GTX 1660 Ti
6346
3DMark Time Spy Extreme
Arc A770
+126%
6525
GeForce GTX 1660 Ti
2883
Blender
Arc A770
+180%
2292
GeForce GTX 1660 Ti
817
Shadow of the Tomb Raider 2160p
Arc A770
+60%
45
GeForce GTX 1660 Ti
28
Shadow of the Tomb Raider 1440p
Arc A770
+53%
80
GeForce GTX 1660 Ti
52
Shadow of the Tomb Raider 1080p
Arc A770
+31%
105
GeForce GTX 1660 Ti
80
Graphics Card
Oct 2022
Release Date
Feb 2019
Alchemist(Arc 7)
Generation
GeForce 16
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
2100 MHz
Base Clock
1500 MHz
2400 MHz
Boost Clock
1770 MHz
2000 MHz
Memory Clock
1500 MHz
Memory
16GB
Memory Size
6GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
192bit
512.0GB/s
Bandwidth
288.0GB/s
Render Config
-
-
-
-
SM Count
24
4096
Shading Units
1536
256
TMUs
96
128
ROPs
48
512
Tensor Cores
-
32
RT Cores
-
-
L1 Cache
64 KB (per SM)
16 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
307.2 GPixel/s
Pixel Rate
84.96 GPixel/s
614.4 GTexel/s
Texture Rate
169.9 GTexel/s
39.32 TFLOPS
FP16 (half)
10.87 TFLOPS
19.66 TFLOPS
FP32 (float)
5.437 TFLOPS
2.458 TFLOPS
FP64 (double)
169.9 GFLOPS
Board Design
225W
TDP
120W
550 W
Suggested PSU
300 W
1x HDMI 2.13x DisplayPort 2.0
Outputs
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
DG2-512
GPU Name
TU116
ACM-G10
GPU Variant
TU116-400-A1
Generation 12.7
Architecture
Turing
TSMC
Foundry
TSMC
6 nm
Process Size
12 nm
21.7 billion
Transistors
6.6 billion
406 mm²
Die Size
284 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
-
CUDA
7.5
6.6
Shader Model
6.6
