Data Center GPU Flex 170 vs Tesla T4
We compared two Professional market GPUs: 16GB VRAM Data Center GPU Flex 170 and 16GB VRAM Tesla T4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Flex 170 's Advantages
Released 3 years and 11 months late
Boost Clock has increased by 29% (2050MHz vs 1590MHz)
Larger VRAM bandwidth (512.0GB/s vs 320.0GB/s)
1536 additional rendering cores
Tesla T4 's Advantages
Lower TDP (70W vs 150W)
Score
Benchmark
FP32 (float)
Data Center GPU Flex 170
+106%
16790
Tesla T4
8141
Graphics Card
Aug 2022
Release Date
Sep 2018
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1950 MHz
Base Clock
585 MHz
2050 MHz
Boost Clock
1590 MHz
2000 MHz
Memory Clock
1250 MHz
Memory
16GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
256bit
512.0GB/s
Bandwidth
320.0GB/s
Render Config
-
SM Count
40
4096
Shading Units
2560
256
TMUs
160
128
ROPs
64
-
Tensor Cores
320
32
RT Cores
40
-
L1 Cache
64 KB (per SM)
16 MB
L2 Cache
4 MB
Theoretical Performance
262.4 GPixel/s
Pixel Rate
101.8 GPixel/s
524.8 GTexel/s
Texture Rate
254.4 GTexel/s
33.59 TFLOPS
FP16 (half)
65.13 TFLOPS
16.79 TFLOPS
FP32 (float)
8.141 TFLOPS
-
FP64 (double)
254.4 GFLOPS
Board Design
150W
TDP
70W
450 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
DG2-512
GPU Name
TU104
ACM-G10
GPU Variant
TU104-895-A1
Generation 12.7
Architecture
Turing
TSMC
Foundry
TSMC
6 nm
Process Size
12 nm
21.7 billion
Transistors
13.6 billion
406 mm²
Die Size
545 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
7.5
6.6
Shader Model
6.6
