GPU Comparison
GEFORCE
NVIDIA GeForce RTX 3090 Ti
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1860 MHz
TDP
450 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
VS
GEFORCE
Quadro K4200
CORE STATE
GK104
VRAM
4 GB
CLOCK SPEED
784 MHz
TDP
108 W
BUS WIDTH
256 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2014
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
RTX 3090 Ti
Quadro K4200
Core Specs
Shading Units
10,752
1,344
-87.5%
Shaders
10,752
1,344
-87.5%
TMUs
336
112
-66.7%
ROPs
112
32
-71.4%
SM Count
84
—
Clocks
Base Clock
1560 MHz
771 MHz
Boost Clock
1860 MHz
784 MHz
Memory Clock
1313 MHz
21 Gbps effective
1350 MHz
5.4 Gbps effective
Memory
Memory Size
24 GB
4 GB
VRAM (MB)
24,576
4,096
-83.3%
Memory Type
GDDR6X
GDDR5
Memory Bus
384 bit
256 bit
Bandwidth
1.01 TB/s
172.8 GB/s
Cache
L1 Cache
128 KB (per SM)
16 KB (per SMX)
L2 Cache
6 MB
512 KB
Performance
Pixel Rate
208.3 GPixel/s
21.95 GPixel/s
Texture Rate
625.0 GTexel/s
87.81 GTexel/s
FP32 (TFLOPS)
40.00 TFLOPS
2.107 TFLOPS
FP64 (TFLOPS)
625.0 GFLOPS (1:64)
87.81 GFLOPS (1:24)
FP16 (TFLOPS)
40.00 TFLOPS (1:1)
—
AI/RT
RT Cores
84
—
Tensor Cores
336
—
Power
TDP
450 W
108 W
TDP (W)
450
108
-76.0%
Suggested PSU
850 W
300 W
Power Connectors
1x 16-pin
1x 6-pin
Architecture
Architecture
Ampere
Kepler
GPU Name
GA102
GK104
Generation
GeForce 30
Quadro Kepler
(Kx200)
Process Size
8 nm
28 nm
Transistors
28,300 million
3,540 million
Die Size
628 mm²
294 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
12.0M / 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
Triple-slot
Single-slot
Length
336 mm
13.2 inches
241 mm
9.5 inches
Height
140 mm
5.5 inches
111 mm
4.4 inches
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x DVI2x DisplayPort 1.2
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Other
Launch Price
1,999 USD
—
Production
End-of-life
End-of-life
Predecessor
GeForce 20
Quadro Fermi
Successor
GeForce 40
Quadro Maxwell