GeForce RTX 3060 Ti GDDR6X vs Arc B570
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GDDR6X and 10GB VRAM Arc B570 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3060 Ti GDDR6X 's Advantages
Larger VRAM bandwidth (608.3GB/s vs 380.0GB/s)
2560 additional rendering cores
Arc B570 's Advantages
Released 2 years and 3 months late
Boost Clock has increased by 50% (2500MHz vs 1665MHz)
More VRAM (10GB vs 8GB)
Lower TDP (150W vs 225W)
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti GDDR6X
+40%
16200
Arc B570
11520
3DMark Time Spy
GeForce RTX 3060 Ti GDDR6X
12223
Arc B570
+3%
12600
3DMark Time Spy Extreme
GeForce RTX 3060 Ti GDDR6X
5941
Arc B570
+1%
6004
3DMark Speed Way
GeForce RTX 3060 Ti GDDR6X
+58%
3097
Arc B570
1948
Graphics Card
Oct 2022
Release Date
Jan 2025
GeForce 30
Generation
Battlemage
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1410 MHz
Base Clock
2500 MHz
1665 MHz
Boost Clock
2500 MHz
1188 MHz
Memory Clock
2375 MHz
Memory
8GB
Memory Size
10GB
GDDR6X
Memory Type
GDDR6
256bit
Memory Bus
160bit
608.3GB/s
Bandwidth
380.0GB/s
Render Config
38
SM Count
-
4864
Shading Units
2304
152
TMUs
144
80
ROPs
80
152
Tensor Cores
144
38
RT Cores
18
128 KB (per SM)
L1 Cache
256 KB (per EU)
4 MB
L2 Cache
18 MB
Theoretical Performance
133.2 GPixel/s
Pixel Rate
200.0 GPixel/s
253.1 GTexel/s
Texture Rate
360.0 GTexel/s
16.20 TFLOPS
FP16 (half)
23.04 TFLOPS
16.20 TFLOPS
FP32 (float)
11.52 TFLOPS
253.1 GFLOPS
FP64 (double)
1440 GFLOPS
Board Design
225W
TDP
150W
550 W
Suggested PSU
450 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1a
3x DisplayPort 2.1
1x 12-pin
Power Connectors
1x 8-pin
Graphics Processor
GA104
GPU Name
BMG-G21
GA104-202-A1
GPU Variant
SRPMG
Ampere
Architecture
Xe2
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
19.6 billion
392 mm²
Die Size
272 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
-
6.7
Shader Model
6.6
