Report an Error

NVIDIA Tesla T4

Graphics Processor
TU104
Cores
2560
TMUs
160
ROPs
64
Memory Size
16 GB
Memory Type
GDDR6
Bus Width
256 bit
GPU Chip
GPU
I/O
I/O
Top
Top
Bottom
Bottom
The Tesla T4 is a professional graphics card by NVIDIA, launched in September 2018. Built on the 12 nm process, and based on the TU104 graphics processor, in its TU104-895-A1 variant, the card supports DirectX 12.0. The TU104 graphics processor is a large chip with a die area of 545 mm² and 13,600 million transistors. Unlike the fully unlocked GeForce RTX 2080 SUPER, which uses the same GPU but has all 3072 shaders enabled, NVIDIA has disabled some shading units on the Tesla T4 to reach the product's target shader count. It features 2560 shading units, 160 texture mapping units and 64 ROPs. Also included are 320 tensor cores which help improve the speed of machine learning applications. The card also has 40 raytracing acceleration cores. NVIDIA has placed 16,384 MB GDDR6 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 585 MHz, which can be boosted up to 1590 MHz, memory is running at 1250 MHz.
Being a single-slot card, the NVIDIA Tesla T4 does not require any additional power connector, its power draw is rated at 70 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla T4 is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 168 mm in length, and features a single-slot cooling solution.

Graphics Processor

GPU Name
TU104
GPU Variant
TU104-895-A1
Architecture
Turing
Foundry
TSMC
Process Size
12 nm
Transistors
13,600 million
Die Size
545 mm²

Graphics Card

Release Date
Sep 13th, 2018
Generation
Tesla
(Txx)
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
2%
Radeon HD 4550
2%
Radeon HD 5450
3%
Radeon HD 6450
3%
GeForce GT 520
3%
GeForce GT 220
5%
GeForce GT 430
5%
Radeon HD 5570
5%
Radeon HD 4670
5%
GeForce GT 440
5%
GeForce GT 240
6%
GeForce 9600 GT
7%
Radeon HD 5670
7%
GeForce GT 640
7%
GeForce 9800 GT
8%
Radeon HD 6670
8%
Radeon HD 4830
8%
Radeon HD 4770
9%
Radeon HD 4850
9%
GeForce GTS 250
9%
GeForce GTS 450
10%
Radeon HD 5750
11%
Radeon HD 7750
11%
Radeon HD 5770
11%
GeForce GTX 260
11%
Radeon HD 4870
11%
Radeon Vega 8
11%
GeForce GTX 550 Ti
12%
GeForce GTX 650
12%
Radeon HD 5830
13%
Radeon HD 6790
13%
Radeon HD 4890
14%
GeForce GTX 460
14%
Radeon RX Vega 11
14%
GeForce GT 1030
14%
GeForce GTX 275
14%
Radeon HD 7770 GHz Edition
14%
GeForce GTX 280
14%
GeForce GTX 465
15%
Radeon HD 6850
15%
GeForce GTX 285
16%
Radeon HD 5850
17%
GeForce GTX 650 Ti
17%
Radeon HD 7790
17%
Radeon RX 550
17%
GeForce GTX 470
18%
Radeon HD 6870
19%
Radeon HD 5870
20%
GeForce GTX 560 Ti
20%
Radeon HD 4870 X2
20%
GeForce GTX 750 Ti
20%
Radeon HD 6950
21%
GeForce GTX 295
21%
GeForce GTX 650 Ti Boost
22%
Radeon HD 7850
22%
GeForce GTX 480
23%
Radeon HD 6970
23%
Radeon R7 265
24%
Radeon RX 460
24%
Radeon R7 370
24%
GeForce GTX 660
24%
GeForce GTX 570
24%
Radeon RX 560
26%
GeForce GTX 950
26%
Radeon HD 7870 GHz Edition
27%
Radeon R9 270X
27%
GeForce GTX 660 Ti
27%
GeForce GTX 580
27%
GeForce GTX 1050
27%
Radeon HD 7950
28%
Radeon HD 5970
29%
GeForce GTX 760
31%
GeForce GTX 670
32%
GeForce GTX 960
33%
Radeon R9 380
33%
Radeon R9 285
33%
Radeon HD 7970
33%
GeForce GTX 680
34%
GeForce GTX 1050 Ti
35%
GeForce GTX 770
36%
Radeon HD 6990
37%
Radeon R9 280X
37%
GeForce GTX 590
37%
Radeon HD 7970 GHz Edition
41%
GeForce GTX 780
43%
GeForce GTX 1650
45%
Radeon RX 470
46%
Radeon R9 290
49%
Radeon RX 570
49%
Radeon R9 390
49%
Radeon R9 290X
50%
GeForce GTX 970
51%
GeForce GTX TITAN
51%
GeForce GTX 780 Ti
52%
Radeon R9 390X
52%
Radeon HD 7990
53%
Radeon RX 480
53%
GeForce GTX 690
56%
Radeon RX 580
57%
GeForce GTX 980
58%
Radeon R9 FURY
58%
GeForce GTX 1060 6 GB
60%
Radeon RX 590
64%
Radeon R9 295X2
64%
GeForce GTX 1660
65%
Radeon R9 FURY X
66%
GeForce GTX 980 Ti
68%
GeForce GTX TITAN X
73%
GeForce GTX 1660 Ti
73%
GeForce GTX 1070
78%
Radeon RX Vega 56
83%
GeForce GTX 1070 Ti
85%
Radeon RX Vega 64
86%
GeForce GTX 1080
86%
GeForce RTX 2060
90%
Radeon RX 5700
97%
GeForce RTX 2060 SUPER
100%
Tesla T4
101%
GeForce RTX 2070
103%
Radeon RX 5700 XT
104%
Radeon VII
107%
TITAN X Pascal
110%
GeForce GTX 1080 Ti
111%
GeForce RTX 2070 SUPER
118%
GeForce RTX 2080
126%
GeForce RTX 2080 SUPER
139%
GeForce RTX 2080 Ti
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
585 MHz
Boost Clock
1590 MHz
Memory Clock
1250 MHz
10000 MHz effective

Memory

Memory Size
16 GB
Memory Type
GDDR6
Memory Bus
256 bit
Bandwidth
320.0 GB/s

Render Config

Shading Units
2560
TMUs
160
ROPs
64
SM Count
40
Tensor Cores
320
RT Cores
40
L1 Cache
64 KB (per SM)
L2 Cache
4 MB

Theoretical Performance

Pixel Rate
101.8 GPixel/s
Texture Rate
254.4 GTexel/s
FP16 (half) performance
65.13 TFLOPS (8:1)
FP32 (float) performance
8.141 TFLOPS
FP64 (double) performance
254.4 GFLOPS (1:32)

Board Design

Slot Width
Single-slot
Length
6.6 inches
168 mm
TDP
70 W
Suggested PSU
350 W
Outputs
No outputs
Power Connectors
None
Board Number
PG183 SKU 200

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.122
CUDA
7.5
Shader Model
6.4