GPU Comparison
GEFORCE
NVIDIA CMP 90HX
CORE STATE
GA102
VRAM
10 GB
CLOCK SPEED
1710 MHz
TDP
320 W
BUS WIDTH
320 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_metal
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 90HX
Quadro K4000
Core Specs
Shading Units
6,400
768
-88.0%
Shaders
6,400
768
-88.0%
TMUs
200
64
-68.0%
ROPs
80
24
-70.0%
SM Count
50
—
Clocks
Base Clock
1500 MHz
—
Boost Clock
1710 MHz
—
GPU Clock
—
810 MHz
Memory Clock
1188 MHz
19 Gbps effective
1404 MHz
5.6 Gbps effective
Memory
Memory Size
10 GB
3 GB
VRAM (MB)
10,240
3,072
-70.0%
Memory Type
GDDR6X
GDDR5
Memory Bus
320 bit
192 bit
Bandwidth
760.3 GB/s
134.8 GB/s
Cache
L1 Cache
128 KB (per SM)
16 KB (per SMX)
L2 Cache
5 MB
384 KB
Performance
Pixel Rate
136.8 GPixel/s
12.96 GPixel/s
Texture Rate
342.0 GTexel/s
51.84 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
1,244.2 GFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
51.84 GFLOPS (1:24)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
—
AI/RT
RT Cores
50
—
Tensor Cores
200
—
Power
TDP
320 W
80 W
TDP (W)
320
80
-75.0%
Suggested PSU
700 W
250 W
Power Connectors
2x 8-pin
1x 6-pin
Architecture
Architecture
Ampere
Kepler
GPU Name
GA102
GK106
Generation
Mining GPUs
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
Dual-slot
Single-slot
Length
285 mm
11.2 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 1.0 x4
PCIe 2.0 x16
Other
Launch Price
—
1,269 USD
Production
End-of-life
End-of-life
Predecessor
—
Quadro Fermi
Successor
—
Quadro Maxwell