GPU Comparison
GEFORCE
NVIDIA A10G
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1710 MHz
TDP
150 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 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_vulkan
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
A10G
Quadro K4000
Core Specs
Shading Units
9,216
768
-91.7%
Shaders
9,216
768
-91.7%
TMUs
288
64
-77.8%
ROPs
96
24
-75.0%
SM Count
72
—
Clocks
Base Clock
1320 MHz
—
Boost Clock
1710 MHz
—
GPU Clock
—
810 MHz
Memory Clock
1563 MHz
12.5 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
GDDR6
GDDR5
Memory Bus
384 bit
192 bit
Bandwidth
600.2 GB/s
134.8 GB/s
Cache
L1 Cache
128 KB (per SM)
16 KB (per SMX)
L2 Cache
6 MB
384 KB
Performance
Pixel Rate
164.2 GPixel/s
12.96 GPixel/s
Texture Rate
492.5 GTexel/s
51.84 GTexel/s
FP32 (TFLOPS)
31.52 TFLOPS
1,244.2 GFLOPS
FP64 (TFLOPS)
985.0 GFLOPS (1:32)
51.84 GFLOPS (1:24)
FP16 (TFLOPS)
31.52 TFLOPS (1:1)
—
AI/RT
RT Cores
72
—
Tensor Cores
288
—
Power
TDP
150 W
80 W
TDP (W)
150
80
-46.7%
Suggested PSU
450 W
250 W
Power Connectors
8-pin EPS
1x 6-pin
Architecture
Architecture
Ampere
Kepler
GPU Name
GA102
GK106
Generation
Server Ampere
(Axx)
Quadro Kepler
(Kx000)
Process Size
8 nm
28 nm
Transistors
28,300 million
2,540 million
Die Size
628 mm²
221 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
11.5M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.2.175
OpenCL
3.0
3.0
CUDA
8.6
3.0
Shader Model
6.8
6.5 (5.1)
Physical
Slot Width
Single-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