NVIDIA Tesla K80 vs NVIDIA Tesla T4

Comparative analysis of NVIDIA Tesla K80 and NVIDIA Tesla T4 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA Tesla K80

NVIDIA Tesla T4

Differences

Reasons to consider the NVIDIA Tesla T4

Videocard is newer: launch date 3 year(s) 9 month(s) later
Around 79% higher core clock speed: 1005 MHz vs 562 MHz
Around 84% higher boost clock speed: 1515 MHz vs 824 MHz
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 28 nm
4x lower typical power consumption: 75 Watt vs 300 Watt
8x more memory clock speed: 10000 MHz vs 1253 MHz, 5 Gbps effective
2.1x better performance in PassMark - G2D Mark: 592 vs 280
2.3x better performance in PassMark - G3D Mark: 10616 vs 4680

Specifications (specs)
Launch date	13 September 2018 vs 17 Nov 2014
Core clock speed	1005 MHz vs 562 MHz
Boost clock speed	1515 MHz vs 824 MHz
Manufacturing process technology	12 nm vs 28 nm
Thermal Design Power (TDP)	75 Watt vs 300 Watt
Memory clock speed	10000 MHz vs 1253 MHz, 5 Gbps effective
Benchmarks
PassMark - G2D Mark	592 vs 280
PassMark - G3D Mark	10616 vs 4680

Compare benchmarks

GPU 1: NVIDIA Tesla K80
GPU 2: NVIDIA Tesla T4

PassMark - G2D Mark

GPU 1

GPU 2

280

592

PassMark - G3D Mark

GPU 1

GPU 2

4680

10616

Name	NVIDIA Tesla K80	NVIDIA Tesla T4
PassMark - G2D Mark	280	592
PassMark - G3D Mark	4680	10616
Geekbench - OpenCL		61276
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		127.622
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		3026.812
CompuBench 1.5 Desktop - T-Rex (Frames/s)		18.798
CompuBench 1.5 Desktop - Video Composition (Frames/s)		119.936
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		910.721
GFXBench 4.0 - Car Chase Offscreen (Frames)		14076
GFXBench 4.0 - Manhattan (Frames)		1976
GFXBench 4.0 - T-Rex (Frames)		1781
GFXBench 4.0 - Car Chase Offscreen (Fps)		14076
GFXBench 4.0 - Manhattan (Fps)		1976
GFXBench 4.0 - T-Rex (Fps)		1781

Compare specifications (specs)

	NVIDIA Tesla K80	NVIDIA Tesla T4
Essentials
Architecture	Kepler 2.0	Turing
Code name	GK210	TU104
Launch date	17 Nov 2014	13 September 2018
Place in performance rating	374	270
Type		Workstation
Technical info
Boost clock speed	824 MHz	1515 MHz
Core clock speed	562 MHz	1005 MHz
Manufacturing process technology	28 nm	12 nm
Peak Double Precision (FP64) Performance	1,371 GFLOPS (1:3)
Peak Single Precision (FP32) Performance	4.113 TFLOPS
Pipelines	2496
Pixel fill rate	42.85 GPixel/s
Texture fill rate	171.4 GTexel/s
Thermal Design Power (TDP)	300 Watt	75 Watt
Transistor count	7100 million	13,600 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Form factor	Dual-slot
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm, 10.5 inches
Recommended system power (PSU)	700 Watt
Supplementary power connectors	1x 8-pin	None
API support
DirectX	12 (11_1)	12.0 (12_1)
OpenCL	3.0
OpenGL	4.6	4.6
Shader Model	6.5 (5.1)
Vulkan
Memory
Maximum RAM amount	12 GB
Memory bandwidth	240.6 GB/s
Memory bus width	384 bit
Memory clock speed	1253 MHz, 5 Gbps effective	10000 MHz
Memory type	GDDR5