Home
NVIDIA Tesla T4
NVIDIA A10 PCIe
NVIDIA Tesla S870
NVIDIA Tesla S1070
NVIDIA Tesla K40m
NVIDIA Tesla M4
NVIDIA Tesla V100 FHHL
NVIDIA Tesla T4
This is a GPU manufactured with TSMC 12nm process, based on Nvidia Turing architecture and released on Sep 2018. It features 13.6 billion transistors, 2560 CUDA cores and 16GB GDDR6 memory, with 4MB L2 cache, theoretical performance of 8.141TFLOPS, with total power consumption of 70W.
Graphics Card
[Report Issues]
Release Date
Sep 2018
Generation
Tesla
Type
Professional
Bus Interface
PCIe 3.0 x16
Clock Speeds
[Report Issues]
Base Clock
585 MHz
Boost Clock
1590 MHz
Memory Clock
1250 MHz
Memory
[Report Issues]
Memory Size
16GB
Memory Type
GDDR6
Memory Bus
256bit
Bandwidth
320.0GB/s
Render Config
[Report Issues]
SM Count
40
Shading Units
2560
TMUs
160
ROPs
64
Tensor Cores
320
RT Cores
40
L1 Cache
64 KB (per SM)
L2 Cache
4 MB
Theoretical Performance
[Report Issues]
Pixel Rate
101.8 GPixel/s
Texture Rate
254.4 GTexel/s
FP16 (half)
65.13 TFLOPS
FP32 (float)
8.141 TFLOPS
FP64 (double)
254.4 GFLOPS
Graphics Processor
[Report Issues]
GPU Name
TU104
GPU Variant
TU104-895-A1
Architecture
Turing
Foundry
TSMC
Process Size
12 nm
Transistors
13.6 billion
Die Size
545 mm²
Board Design
[Report Issues]
TDP
70W
Suggested PSU
250 W
Outputs
No outputs
Power Connectors
None
Graphics Features
[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
7.5
Shader Model
6.6
Rankings
[Report Issues]
FP32 (float)
3DMark Time Spy
3DMark Time Spy Extreme
3DMark Speed Way
Blender
OctaneBench