GPU Comparison
GEFORCE
NVIDIA PG506-232
CORE STATE
GA100
VRAM
24 GB
CLOCK SPEED
1440 MHz
TDP
165 W
BUS WIDTH
3072 bit
ARCHITECTURE
Ampere
PROCESS
7 nm
LAUNCH DATE
2021
VS
GEFORCE
Quadro K4000
CORE STATE
GK106
VRAM
3 GB
CLOCK SPEED
—
TDP
80 W
BUS WIDTH
192 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_metal
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
PG506-232
Quadro K4000
Core Specs
Shading Units
3,584
768
-78.6%
Shaders
3,584
768
-78.6%
TMUs
224
64
-71.4%
ROPs
96
24
-75.0%
SM Count
56
—
Clocks
Base Clock
930 MHz
—
Boost Clock
1440 MHz
—
GPU Clock
—
810 MHz
Memory Clock
1215 MHz
2.4 Gbps effective
1404 MHz
5.6 Gbps effective
Memory
Memory Size
24 GB
3 GB
VRAM (MB)
24,576
3,072
-87.5%
Memory Type
HBM2
GDDR5
Memory Bus
3072 bit
192 bit
Bandwidth
933.1 GB/s
134.8 GB/s
Cache
L1 Cache
192 KB (per SM)
16 KB (per SMX)
L2 Cache
24 MB
384 KB
Performance
Pixel Rate
138.2 GPixel/s
12.96 GPixel/s
Texture Rate
322.6 GTexel/s
51.84 GTexel/s
FP32 (TFLOPS)
10.32 TFLOPS
1,244.2 GFLOPS
FP64 (TFLOPS)
5.161 TFLOPS (1:2)
51.84 GFLOPS (1:24)
FP16 (TFLOPS)
10.32 TFLOPS (1:1)
—
AI/RT
Tensor Cores
224
—
Power
TDP
165 W
80 W
TDP (W)
165
80
-51.5%
Suggested PSU
450 W
250 W
Power Connectors
8-pin EPS
1x 6-pin
Architecture
Architecture
Ampere
Kepler
GPU Name
GA100
GK106
Generation
Server Ampere
(Axx)
Quadro Kepler
(Kx000)
Process Size
7 nm
28 nm
Transistors
54,200 million
2,540 million
Die Size
826 mm²
221 mm²
Foundry
TSMC
TSMC
Density
65.6M / mm²
11.5M / mm²
API Support
DirectX
—
12 (11_0)
OpenGL
—
4.6
Vulkan
—
1.2.175
OpenCL
3.0
3.0
CUDA
8.0
3.0
Shader Model
—
6.5 (5.1)
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
241 mm
9.5 inches
Height
112 mm
4.4 inches
111 mm
4.4 inches
Outputs
No outputs
1x DVI2x DisplayPort 1.2
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Other
Launch Price
—
1,269 USD
Production
End-of-life
End-of-life
Predecessor
Tesla Turing
Quadro Fermi
Successor
Server Ada
Quadro Maxwell