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
Front 2
Front 2
The Tesla T4 is a professional graphics card by NVIDIA, launched on September 13th, 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 Ultimate. 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 paired 16 GB GDDR6 memory with the Tesla T4, 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 (10 Gbps effective).
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
Density
25.0M / mm²
Die Size
545 mm²
Chip Package
BGA-2228

Graphics Card

Release Date
Sep 13th, 2018
Generation
Tesla Turing
(Txx)
Predecessor
Tesla Volta
Successor
Tesla Ampere
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

GeForce 210
1%
GeForce 9400 GT
1%
Radeon HD 4550
2%
Radeon HD 5450
2%
Radeon HD 6450
3%
GeForce GT 520
3%
GeForce GT 220
3%
GeForce GT 430
5%
Radeon HD 5570
5%
Radeon HD 4670
5%
GeForce GT 440
5%
GeForce GT 240
5%
GeForce 9600 GT
6%
Radeon HD 5670
7%
GeForce GT 640
7%
GeForce 9800 GT
7%
Radeon HD 6670
8%
Radeon HD 4830
8%
Radeon HD 4770
8%
Radeon HD 4850
9%
GeForce GTS 250
9%
GeForce GTS 450
9%
Radeon HD 5750
10%
Radeon HD 7750
11%
Radeon HD 5770
11%
GeForce GTX 260
11%
Radeon HD 4870
11%
Radeon Vega 8
11%
GeForce GTX 550 Ti
11%
GeForce GTX 650
12%
Radeon HD 5830
12%
Radeon HD 6790
13%
Radeon HD 4890
13%
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
14%
Radeon HD 6850
15%
GeForce GTX 285
15%
Radeon HD 5850
16%
GeForce GTX 650 Ti
17%
Radeon HD 7790
17%
Radeon RX 550
17%
GeForce GTX 470
17%
Radeon HD 6870
18%
Radeon HD 5870
19%
GeForce GTX 560 Ti
20%
Radeon HD 4870 X2
20%
GeForce GTX 750 Ti
20%
Radeon HD 6950
20%
GeForce GTX 295
21%
GeForce GTX 650 Ti Boost
21%
Radeon HD 7850
22%
GeForce GTX 480
22%
Radeon HD 6970
23%
Radeon R7 265
23%
Radeon RX 460
24%
Radeon R7 370
24%
GeForce GTX 660
24%
GeForce GTX 570
24%
Radeon RX 560
24%
GeForce GTX 950
26%
Radeon HD 7870 GHz Edition
26%
Radeon R9 270X
27%
GeForce GTX 660 Ti
27%
GeForce GTX 580
27%
GeForce GTX 1050
27%
Radeon HD 7950
27%
GeForce GTX 1630
28%
Radeon HD 5970
28%
GeForce GTX 760
29%
GeForce GTX 670
31%
GeForce GTX 960
32%
Radeon R9 380
33%
Radeon R9 285
33%
Radeon HD 7970
33%
GeForce GTX 680
33%
GeForce GTX 1050 Ti
34%
GeForce GTX 770
35%
Radeon HD 6990
36%
Radeon R9 280X
37%
GeForce GTX 590
37%
Radeon HD 7970 GHz Edition
37%
GeForce GTX 780
41%
Arc A380
41%
Radeon RX 6400
42%
GeForce GTX 1650
43%
Radeon RX 470
45%
Radeon R9 290
46%
Radeon RX 570
49%
Radeon R9 390
49%
Radeon R9 290X
49%
GeForce GTX 970
50%
GeForce GTX TITAN
51%
GeForce GTX 780 Ti
51%
Radeon R9 390X
52%
Radeon HD 7990
52%
Radeon RX 480
53%
GeForce GTX 690
53%
GeForce GTX 1060 6 GB
55%
Radeon RX 5500 OEM
55%
Radeon RX 580
56%
Radeon RX 5500 XT
56%
Radeon RX 6500 XT
57%
GeForce GTX 980
57%
GeForce GTX 1650 SUPER
58%
Radeon R9 FURY
58%
Radeon RX 590
60%
Radeon R9 295X2
64%
GeForce GTX 1660
64%
Radeon R9 FURY X
65%
GeForce GTX 980 Ti
66%
GeForce GTX TITAN X
68%
GeForce GTX 1660 SUPER
70%
GeForce GTX 1070
73%
GeForce GTX 1660 Ti
73%
GeForce RTX 3050 8 GB
75%
Radeon RX Vega 56
78%
GeForce GTX 1070 Ti
83%
Radeon RX 5600 XT
84%
Radeon RX Vega 64
85%
GeForce GTX 1080
86%
GeForce RTX 2060
86%
Radeon RX 5700
90%
Arc A580
90%
Radeon RX 6600
94%
GeForce RTX 2060 SUPER
97%
GeForce RTX 2070
98%
Radeon RX 5700 XT
98%
Tesla T4
100%
GeForce RTX 3060 12 GB
100%
Arc A750
104%
Radeon VII
104%
TITAN X Pascal
107%
Radeon RX 6600 XT
108%
GeForce GTX 1080 Ti
110%
Arc A770
111%
GeForce RTX 2070 SUPER
111%
Radeon RX 6650 XT
117%
Radeon RX 7600
118%
GeForce RTX 4060
119%
GeForce RTX 2080
120%
Radeon RX 7600 XT
122%
GeForce RTX 2080 SUPER
126%
GeForce RTX 3060 Ti
129%
Radeon RX 6700 XT
133%
Radeon RX 6750 XT
141%
GeForce RTX 4060 Ti 8 GB
143%
GeForce RTX 2080 Ti
144%
GeForce RTX 3070
151%
GeForce RTX 3070 Ti
161%
Radeon RX 7700 XT
163%
Radeon RX 6800
166%
GeForce RTX 4070
184%
Radeon RX 6800 XT
189%
GeForce RTX 3080
196%
Radeon RX 7800 XT
198%
Radeon RX 6900 XT
203%
GeForce RTX 4070 SUPER
213%
Radeon RX 7900 GRE
217%
GeForce RTX 3080 Ti
219%
Radeon RX 6950 XT
220%
GeForce RTX 3090
223%
GeForce RTX 4070 Ti
229%
GeForce RTX 4070 Ti SUPER
250%
Radeon RX 7900 XT
257%
GeForce RTX 3090 Ti
259%
GeForce RTX 4080
291%
GeForce RTX 4080 SUPER
295%
Radeon RX 7900 XTX
298%
GeForce RTX 4090
365%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
585 MHz
Boost Clock
1590 MHz
Memory Clock
1250 MHz
10 Gbps 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)
65.13 TFLOPS (8:1)
FP32 (float)
8.141 TFLOPS
FP64 (double)
254.4 GFLOPS (1:32)

Board Design

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

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
7.5
Shader Model
6.7

TU104 GPU Notes

Ray Tracing Cores: 1st Gen
Tensor Cores: 2nd Gen
NVENC: 7th Gen
NVDEC: 4th Gen
PureVideo HD: VP10
VDPAU: Feature Set J
Apr 17th, 2024 22:22 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts