NVIDIA GeForce GTX 680 vs Intel Arc A350
We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 680 and 4GB VRAM Arc A350 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 680 's Advantages
Larger VRAM bandwidth (192.3GB/s vs 124.0GB/s)
768 additional rendering cores
Intel Arc A350 's Advantages
Released 9 years and 10 months late
Boost Clock has increased by 89% (2000MHz vs 1058MHz)
More VRAM (4GB vs 2GB)
Lower TDP (25W vs 195W)
Score
Benchmark
FP32 (float)
GeForce GTX 680
+5%
3.25 TFLOPS
Arc A350
3.072 TFLOPS
3DMark Time Spy
GeForce GTX 680
2004
Arc A350
+61%
3239
Graphics Card
Mar 2012
Release Date
Jan 2022
GeForce 600
Generation
Alchemist(Arc 3)
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1006 MHz
Base Clock
2000 MHz
1058 MHz
Boost Clock
2000 MHz
1502 MHz
Memory Clock
1937 MHz
Memory
2GB
Memory Size
4GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
64bit
192.3GB/s
Bandwidth
124.0GB/s
Render Config
-
-
-
-
-
-
1536
Shading Units
768
128
TMUs
48
32
ROPs
24
-
Tensor Cores
96
-
RT Cores
6
16 KB (per SMX)
L1 Cache
-
512 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
33.86 GPixel/s
Pixel Rate
48.00 GPixel/s
135.4 GTexel/s
Texture Rate
96.00 GTexel/s
-
FP16 (half)
6.144 TFLOPS
3.250 TFLOPS
FP32 (float)
3.072 TFLOPS
135.4 GFLOPS
FP64 (double)
768.0 GFLOPS
Board Design
195W
TDP
25W
450 W
Suggested PSU
200 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
No outputs
2x 6-pin
Power Connectors
-
Graphics Processor
GK104
GPU Name
DG2-128
GK104-400-A2
GPU Variant
ACM-G11
Kepler
Architecture
Generation 12.7
TSMC
Foundry
TSMC
28 nm
Process Size
6 nm
3.54 billion
Transistors
7.2 billion
294 mm²
Die Size
157 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
-
5.1
Shader Model
6.6
