NVIDIA Quadro RTX 4000 vs NVIDIA Tesla K20X

GPU Specs Compare

G

NVIDIA Quadro RTX 4000

NVIDIA 2018-11
G

NVIDIA Tesla K20X

NVIDIA 2012-11

Graphics Card

Release Date
Nov 2018
Nov 2012
Generation
Quadro Turing
Tesla
Type
Professional
Professional
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16

Clock Speeds

Base Clock
1005 MHz
-
Boost Clock
1545 MHz
-
Memory Clock
1625 MHz
1300 MHz

Memory

Memory Size
8GB
6GB
Memory Type
GDDR6
GDDR5
Memory Bus
256bit
384bit
Bandwidth
416.0GB/s
249.6GB/s

Render Config

SM Count
36
-
Shading Units
2304
2688
TMUs
144
224
ROPs
64
48
Tensor Cores
288
-
RT Cores
36
-
L1 Cache
64 KB (per SM)
16 KB (per SMX)
L2 Cache
4 MB
1536 KB

Theoretical Performance

Pixel Rate
98.88 GPixel/s
40.99 GPixel/s
Texture Rate
222.5 GTexel/s
164.0 GTexel/s
FP16 (half)
14.24 TFLOPS
-
FP32 (float)
7.119 TFLOPS
3.935 TFLOPS
FP64 (double)
222.5 GFLOPS
1312 GFLOPS

Graphics Processor

GPU Name
TU104
GK110
GPU Variant
TU104-850-A1
-
Architecture
Turing
Kepler
Foundry
TSMC
TSMC
Process Size
12 nm
28 nm
Transistors
13.6 billion
7.08 billion
Die Size
545 mm²
561 mm²

Board Design

TDP
160W
235W
Suggested PSU
450 W
550 W
Outputs
3x DisplayPort 1.4a1x USB Type-C
No outputs
Power Connectors
1x 8-pin
1x 6-pin + 1x 8-pin

Graphics Features

DirectX
12 Ultimate (12_2)
12 (11_0)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.1
CUDA
7.5
3.5
Shader Model
6.8
5.1

📊 Benchmark

3DMark Time Spy
7,853
-
3DMark Time Spy Extreme
3,696
-