GPU Comparison
GEFORCE
NVIDIA Quadro K620M
CORE STATE
GM108S
VRAM
2 GB
CLOCK SPEED
1124 MHz
TDP
30 W
BUS WIDTH
64 bit
ARCHITECTURE
Maxwell
PROCESS
28 nm
LAUNCH DATE
2015
VS
GEFORCE
Quadro P2000
CORE STATE
GP106
VRAM
5 GB
CLOCK SPEED
1480 MHz
TDP
75 W
BUS WIDTH
160 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
Quadro K620M
Quadro P2000
Core Specs
Shading Units
384
1,024
+166.7%
Shaders
384
1,024
+166.7%
TMUs
16
64
+300.0%
ROPs
8
40
+400.0%
SM Count
—
8
Clocks
Base Clock
1029 MHz
1076 MHz
Boost Clock
1124 MHz
1480 MHz
Memory Clock
1001 MHz
2 Gbps effective
1752 MHz
7 Gbps effective
Memory
Memory Size
2 GB
5 GB
VRAM (MB)
2,048
5,120
+150.0%
Memory Type
DDR3
GDDR5
Memory Bus
64 bit
160 bit
Bandwidth
16.02 GB/s
140.2 GB/s
Cache
L1 Cache
64 KB (per SMM)
48 KB (per SM)
L2 Cache
1024 KB
1280 KB
Performance
Pixel Rate
8.992 GPixel/s
59.20 GPixel/s
Texture Rate
17.98 GTexel/s
94.72 GTexel/s
FP32 (TFLOPS)
863.2 GFLOPS
3.031 TFLOPS
FP64 (TFLOPS)
26.98 GFLOPS (1:32)
94.72 GFLOPS (1:32)
FP16 (TFLOPS)
—
47.36 GFLOPS (1:64)
Power
TDP
30 W
75 W
TDP (W)
30
75
+150.0%
Suggested PSU
—
250 W
Power Connectors
None
None
Architecture
Architecture
Maxwell
Pascal
GPU Name
GM108S
GP106
Generation
Quadro Kepler-M
(Kx200M)
Quadro Pascal
(Px000)
Process Size
28 nm
16 nm
Transistors
1,020 million
4,400 million
Die Size
77 mm²
200 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
22.0M / mm²
API Support
DirectX
12 (11_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
5.0
6.1
Shader Model
6.7 (5.1)
6.8
Physical
Slot Width
MXM Module
Single-slot
Length
—
196 mm
7.7 inches
Height
—
111 mm
4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 1.4a
Bus Interface
MXM-A (3.0)
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Quadro Fermi-M
Quadro Maxwell
Successor
Quadro Maxwell-M
Quadro Volta