NVIDIA Tesla T4 vs NVIDIA Tesla M10

Comparative analysis of NVIDIA Tesla T4 and NVIDIA Tesla M10 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: Geekbench - OpenCL, GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), PassMark - G2D Mark, PassMark - G3D Mark.

 

Differences

Reasons to consider the NVIDIA Tesla T4

  • Videocard is newer: launch date 2 year(s) 3 month(s) later
  • Around 16% higher boost clock speed: 1515 MHz vs 1306 MHz
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 28 nm
  • 3x lower typical power consumption: 75 Watt vs 225 Watt
  • Around 92% higher memory clock speed: 10000 MHz vs 5200 MHz
  • Around 35% better performance in Geekbench - OpenCL: 66585 vs 49282
  • 2.7x better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 14076 vs 5204
  • 2.7x better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 14076 vs 5204
  • Around 8% better performance in PassMark - G2D Mark: 566 vs 522
  • 3.2x better performance in PassMark - G3D Mark: 11184 vs 3490
Specifications (specs)
Launch date 13 September 2018 vs 18 May 2016
Boost clock speed 1515 MHz vs 1306 MHz
Manufacturing process technology 12 nm vs 28 nm
Thermal Design Power (TDP) 75 Watt vs 225 Watt
Memory clock speed 10000 MHz vs 5200 MHz
Benchmarks
Geekbench - OpenCL 66585 vs 49282
GFXBench 4.0 - Car Chase Offscreen (Frames) 14076 vs 5204
GFXBench 4.0 - Car Chase Offscreen (Fps) 14076 vs 5204
PassMark - G2D Mark 566 vs 522
PassMark - G3D Mark 11184 vs 3490

Reasons to consider the NVIDIA Tesla M10

  • Around 3% higher core clock speed: 1033 MHz vs 1005 MHz
  • Around 84% better performance in GFXBench 4.0 - Manhattan (Frames): 3693 vs 2002
  • Around 84% better performance in GFXBench 4.0 - Manhattan (Fps): 3693 vs 2002
  • Around 82% better performance in GFXBench 4.0 - T-Rex (Frames): 3306 vs 1819
  • Around 82% better performance in GFXBench 4.0 - T-Rex (Fps): 3306 vs 1819
Specifications (specs)
Core clock speed 1033 MHz vs 1005 MHz
Benchmarks
GFXBench 4.0 - Manhattan (Frames) 3693 vs 2002
GFXBench 4.0 - Manhattan (Fps) 3693 vs 2002
GFXBench 4.0 - T-Rex (Frames) 3306 vs 1819
GFXBench 4.0 - T-Rex (Fps) 3306 vs 1819

Compare benchmarks

GPU 1: NVIDIA Tesla T4
GPU 2: NVIDIA Tesla M10

Geekbench - OpenCL
GPU 1
GPU 2
66585
49282
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
2002
3693
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
2002
3693
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
1819
3306
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
1819
3306
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
14076
5204
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
14076
5204
PassMark - G2D Mark
GPU 1
GPU 2
566
522
PassMark - G3D Mark
GPU 1
GPU 2
11184
3490
Name NVIDIA Tesla T4 NVIDIA Tesla M10
Geekbench - OpenCL 66585 49282
GFXBench 4.0 - Manhattan (Frames) 2002 3693
GFXBench 4.0 - Manhattan (Fps) 2002 3693
GFXBench 4.0 - T-Rex (Frames) 1819 3306
GFXBench 4.0 - T-Rex (Fps) 1819 3306
GFXBench 4.0 - Car Chase Offscreen (Frames) 14076 5204
GFXBench 4.0 - Car Chase Offscreen (Fps) 14076 5204
PassMark - G2D Mark 566 522
PassMark - G3D Mark 11184 3490

Compare specifications (specs)

NVIDIA Tesla T4 NVIDIA Tesla M10

Essentials

Architecture Turing Maxwell
Code name TU104 GM107
Launch date 13 September 2018 18 May 2016
Place in performance rating 145 285
Type Workstation Workstation

Technical info

Boost clock speed 1515 MHz 1306 MHz
Core clock speed 1005 MHz 1033 MHz
Manufacturing process technology 12 nm 28 nm
Thermal Design Power (TDP) 75 Watt 225 Watt
Transistor count 13,600 million 1,870 million
Floating-point performance 4x 1,672 gflops
Pipelines 4x 640
Texture fill rate 4x 52.24 GTexel / s billion / sec

Video outputs and ports

Display Connectors No outputs No outputs

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors None 1x 8-pin
Length 267 mm

API support

DirectX 12.0 (12_1) 12.0 (11_0)
OpenGL 4.6 4.6

Memory

Memory clock speed 10000 MHz 5200 MHz
Maximum RAM amount 4x 8 GB
Memory bandwidth 4x 83.2 GB / s
Memory bus width 4x 128 Bit
Memory type GDDR5