GeForce RTX 3070 vs GeForce GTX 680 Mac Edition
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 2GB VRAM GeForce GTX 680 Mac Edition to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Released 7 years and 5 months late
Boost Clock has increased by 63% (1725MHz vs 1058MHz)
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (448.0GB/s vs 192.3GB/s)
4352 additional rendering cores
GeForce GTX 680 Mac Edition 's Advantages
Lower TDP (195W vs 220W)
Score
Benchmark
FP32 (float)
GeForce RTX 3070
+524%
20310
GeForce GTX 680 Mac Edition
3250
Graphics Card
Sep 2020
Release Date
Apr 2013
GeForce 30
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1500 MHz
Base Clock
1006 MHz
1725 MHz
Boost Clock
1058 MHz
1750 MHz
Memory Clock
1502 MHz
Memory
8GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
192.3GB/s
Render Config
46
SM Count
-
5888
Shading Units
1536
184
TMUs
128
96
ROPs
32
184
Tensor Cores
-
46
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per SMX)
4 MB
L2 Cache
512 KB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
33.86 GPixel/s
317.4 GTexel/s
Texture Rate
135.4 GTexel/s
20.31 TFLOPS
FP16 (half)
-
20.31 TFLOPS
FP32 (float)
3.250 TFLOPS
317.4 GFLOPS
FP64 (double)
135.4 GFLOPS
Board Design
220W
TDP
195W
550 W
Suggested PSU
450 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
1x 12-pin
Power Connectors
2x 6-pin
Graphics Processor
GA104
GPU Name
GK104
GA104-300-A1
GPU Variant
GK104-400-A2
Ampere
Architecture
Kepler
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
17.4 billion
Transistors
3.54 billion
392 mm²
Die Size
294 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
8.6
CUDA
3.0
6.6
Shader Model
5.1
