NVIDIA GeForce RTX 4070 GDDR6 vs NVIDIA Tesla K20s

GPU Specs Compare

Graphics Card

Release Date
Aug 2024
Feb 2013
Generation
GeForce 40
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16

Clock Speeds

Base Clock
1920 MHz
-
Boost Clock
2475 MHz
-
Memory Clock
2500 MHz
1300 MHz

Memory

Memory Size
12GB
5GB
Memory Type
GDDR6
GDDR5
Memory Bus
192bit
320bit
Bandwidth
480.0GB/s
208.0GB/s

Render Config

SM Count
46
-
Shading Units
5888
2496
TMUs
184
208
ROPs
64
40
Tensor Cores
184
-
RT Cores
46
-
L1 Cache
128 KB (per SM)
16 KB (per SMX)
L2 Cache
36 MB
1280 KB

Theoretical Performance

Pixel Rate
158.4 GPixel/s
29.90 GPixel/s
Texture Rate
455.4 GTexel/s
119.6 GTexel/s
FP16 (half)
29.15 TFLOPS
-
FP32 (float)
29.15 TFLOPS
2.870 TFLOPS
FP64 (double)
455.4 GFLOPS
956.8 GFLOPS

Graphics Processor

GPU Name
AD104
GK110
GPU Variant
AD104-2XX-A1
-
Architecture
Ada Lovelace
Kepler
Foundry
TSMC
TSMC
Process Size
5 nm
28 nm
Transistors
35.8 billion
7.08 billion
Die Size
294 mm²
561 mm²

Board Design

TDP
200W
225W
Suggested PSU
550 W
550 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-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
8.9
3.5
Shader Model
6.8
5.1