Intel Arc B580 vs NVIDIA GeForce RTX 3090 Ti
We compared two Desktop platform GPUs: 12GB VRAM Arc B580 and 24GB VRAM GeForce RTX 3090 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Arc B580 's Advantages
Released 2 years and 11 months late
Boost Clock has increased by 44% (2670MHz vs 1860MHz)
Lower TDP (190W vs 450W)
NVIDIA GeForce RTX 3090 Ti 's Advantages
More VRAM (24GB vs 12GB)
Larger VRAM bandwidth (1008GB/s vs 456.0GB/s)
8192 additional rendering cores
Score
Benchmark
FP32 (float)
Arc B580
13.67 TFLOPS
GeForce RTX 3090 Ti
+192%
40 TFLOPS
3DMark Time Spy
Arc B580
14701
GeForce RTX 3090 Ti
+48%
21832
3DMark Time Spy Extreme
Arc B580
7068
GeForce RTX 3090 Ti
+60%
11318
3DMark Speed Way
Arc B580
2478
GeForce RTX 3090 Ti
+138%
5903
Blender
Arc B580
1690
GeForce RTX 3090 Ti
+267%
6217
Cyberpunk 2077 1440p
Arc B580
63
GeForce RTX 3090 Ti
+38%
87
GTA 5 1440p
Arc B580
146
GeForce RTX 3090 Ti
+28%
187
Graphics Card
Dec 2024
Release Date
Jan 2022
Battlemage
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 4.0 x16
Clock Speeds
2670 MHz
Base Clock
1560 MHz
2670 MHz
Boost Clock
1860 MHz
2375 MHz
Memory Clock
1313 MHz
Memory
12GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6X
192bit
Memory Bus
384bit
456.0GB/s
Bandwidth
1008GB/s
Render Config
-
-
-
-
SM Count
84
2560
Shading Units
10752
160
TMUs
336
80
ROPs
112
160
Tensor Cores
336
20
RT Cores
84
256 KB (per EU)
L1 Cache
128 KB (per SM)
18 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
213.6 GPixel/s
Pixel Rate
208.3 GPixel/s
427.2 GTexel/s
Texture Rate
625.0 GTexel/s
27.34 TFLOPS
FP16 (half)
40.00 TFLOPS
13.67 TFLOPS
FP32 (float)
40.00 TFLOPS
1.709 TFLOPS
FP64 (double)
625.0 GFLOPS
Board Design
190W
TDP
450W
450 W
Suggested PSU
850 W
1x HDMI 2.1a
3x DisplayPort 2.1
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
BMG-G21
GPU Name
GA102
SRPMF
GPU Variant
GA102-350-A1
Xe2
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
19.6 billion
Transistors
28.3 billion
272 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
1.4
Vulkan
1.3
-
CUDA
8.6
6.6
Shader Model
6.6
