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
RTX 4500 Ada Generation
CORE STATE
AD103
VRAM
24 GB
CLOCK SPEED
2580 MHz
TDP
210 W
BUS WIDTH
192 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Quadro K620M
RTX 4500 Ada Generation
Core Specs
Shading Units
384
7,680
+1900.0%
Shaders
384
7,680
+1900.0%
TMUs
16
240
+1400.0%
ROPs
8
80
+900.0%
SM Count
—
60
Clocks
Base Clock
1029 MHz
2070 MHz
Boost Clock
1124 MHz
2580 MHz
Memory Clock
1001 MHz
2 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
2 GB
24 GB
VRAM (MB)
2,048
24,576
+1100.0%
Memory Type
DDR3
GDDR6
Memory Bus
64 bit
192 bit
Bandwidth
16.02 GB/s
432.0 GB/s
Cache
L1 Cache
64 KB (per SMM)
128 KB (per SM)
L2 Cache
1024 KB
48 MB
Performance
Pixel Rate
8.992 GPixel/s
206.4 GPixel/s
Texture Rate
17.98 GTexel/s
619.2 GTexel/s
FP32 (TFLOPS)
863.2 GFLOPS
39.63 TFLOPS
FP64 (TFLOPS)
26.98 GFLOPS (1:32)
619.2 GFLOPS (1:64)
FP16 (TFLOPS)
—
39.63 TFLOPS (1:1)
AI/RT
RT Cores
—
60
Tensor Cores
—
240
Power
TDP
30 W
210 W
TDP (W)
30
210
+600.0%
Suggested PSU
—
550 W
Power Connectors
None
None
Architecture
Architecture
Maxwell
Ada Lovelace
GPU Name
GM108S
AD103
Generation
Quadro Kepler-M
(Kx200M)
Workstation Ada
(x000A)
Process Size
28 nm
5 nm
Transistors
1,020 million
45,900 million
Die Size
77 mm²
379 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
121.1M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
5.0
8.9
Shader Model
6.7 (5.1)
6.8
Physical
Slot Width
MXM Module
Dual-slot
Length
—
245 mm
9.6 inches
Height
—
112 mm
4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 1.4a
Bus Interface
MXM-A (3.0)
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
Quadro Fermi-M
Workstation Ampere
Successor
Quadro Maxwell-M
Blackwell PRO W