GeForce RTX 3070 vs GeForce GT 640 Rev. 2
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 1024MB VRAM GeForce GT 640 Rev. 2 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 4 months late
Boost Clock1725MHz
More VRAM (8GB vs 1024GB)
Larger VRAM bandwidth (448.0GB/s vs 40.06GB/s)
5504 additional rendering cores
GeForce GT 640 Rev. 2 's Advantages
Lower TDP (49W vs 220W)
Score
Benchmark
FP32 (float)
GeForce RTX 3070
+2429%
20310
GeForce GT 640 Rev. 2
803
Graphics Card
Sep 2020
Release Date
May 2013
GeForce 30
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x8
Clock Speeds
1500 MHz
Base Clock
-
1725 MHz
Boost Clock
-
1750 MHz
Memory Clock
1252 MHz
Memory
8GB
Memory Size
1024MB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
64bit
448.0GB/s
Bandwidth
40.06GB/s
Render Config
46
SM Count
-
5888
Shading Units
384
184
TMUs
32
96
ROPs
8
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
8.368 GPixel/s
317.4 GTexel/s
Texture Rate
33.47 GTexel/s
20.31 TFLOPS
FP16 (half)
-
20.31 TFLOPS
FP32 (float)
803.3 GFLOPS
317.4 GFLOPS
FP64 (double)
33.47 GFLOPS
Board Design
220W
TDP
49W
550 W
Suggested PSU
200 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 1.4a
1x VGA
1x 12-pin
Power Connectors
None
Graphics Processor
GA104
GPU Name
GK208
GA104-300-A1
GPU Variant
GK208-400-A1
Ampere
Architecture
Kepler 2.0
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
17.4 billion
Transistors
1.02 billion
392 mm²
Die Size
87 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
3.5
6.6
Shader Model
5.1
