Report an Error

NVIDIA GeForce GTX 780 Ti 6 GB

Graphics Processor
GK110B
Cores
2880
TMUs
240
ROPs
48
Memory Size
6 GB
Memory Type
GDDR5
Bus Width
384 bit
The GeForce GTX 780 Ti 6 GB was a graphics card by NVIDIA, that was never released. Built on the 28 nm process, and based on the GK110B graphics processor, the card supports DirectX 12.0. The GK110B graphics processor is a large chip with a die area of 561 mm² and 7,080 million transistors. It features 2880 shading units, 240 texture mapping units and 48 ROPs. NVIDIA has placed 6,144 MB GDDR5 memory on the card, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 875 MHz, which can be boosted up to 928 MHz, memory is running at 1753 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 780 Ti 6 GB draws power from 1x 6-pin + 1x 8-pin power connectors, with power draw rated at 250 W maximum. Display outputs include: 2x DVI, 1x HDMI, 1x DisplayPort. GeForce GTX 780 Ti 6 GB is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution.

Graphics Processor

GPU Name
GK110B
Architecture
Kepler
Foundry
TSMC
Process Size
28 nm
Transistors
7,080 million
Die Size
561 mm²

Graphics Card

Release Date
Never Released
Generation
GeForce 700
Production
End-of-life
Bus Interface
PCIe 3.0 x16
Reviews
94 in our database

Relative Performance

2%
GeForce 210
3%
GeForce 9400 GT
3%
Radeon HD 4550
4%
Radeon HD 5450
5%
Radeon HD 6450
5%
GeForce GT 520
7%
GeForce GT 220
9%
GeForce GT 430
9%
Radeon HD 5570
10%
Radeon HD 4670
10%
GeForce GT 440
10%
GeForce GT 240
12%
GeForce 9600 GT
13%
Radeon HD 5670
14%
GeForce GT 640
14%
GeForce 9800 GT
15%
Radeon HD 6670
15%
Radeon HD 4830
16%
Radeon HD 4770
17%
Radeon HD 4850
17%
GeForce GTS 250
18%
GeForce GTS 450
19%
Radeon HD 5750
21%
Radeon HD 7750
21%
Radeon HD 5770
22%
GeForce GTX 260
22%
Radeon HD 4870
22%
Radeon Vega 8
22%
GeForce GTX 550 Ti
22%
GeForce GTX 650
24%
Radeon HD 5830
25%
Radeon HD 6790
25%
Radeon HD 4890
26%
GeForce GTX 460
27%
Radeon RX Vega 11
27%
GeForce GT 1030
27%
GeForce GTX 275
27%
Radeon HD 7770 GHz Edition
27%
GeForce GTX 280
28%
GeForce GTX 465
29%
Radeon HD 6850
30%
GeForce GTX 285
32%
Radeon HD 5850
32%
GeForce GTX 650 Ti
32%
Radeon HD 7790
34%
Radeon RX 550
34%
GeForce GTX 470
35%
Radeon HD 6870
37%
Radeon HD 5870
39%
GeForce GTX 560 Ti
39%
Radeon HD 4870 X2
40%
GeForce GTX 750 Ti
40%
Radeon HD 6950
41%
GeForce GTX 295
42%
GeForce GTX 650 Ti Boost
42%
Radeon HD 7850
43%
GeForce GTX 480
45%
Radeon HD 6970
45%
Radeon R7 265
46%
Radeon RX 460
46%
Radeon R7 370
46%
GeForce GTX 660
46%
GeForce GTX 570
47%
Radeon RX 560
50%
GeForce GTX 950
51%
Radeon HD 7870 GHz Edition
52%
Radeon R9 270X
52%
GeForce GTX 660 Ti
53%
GeForce GTX 580
53%
GeForce GTX 1050
53%
Radeon HD 7950
54%
Radeon HD 5970
56%
GeForce GTX 760
60%
GeForce GTX 670
62%
GeForce GTX 960
63%
Radeon R9 380
64%
Radeon R9 285
64%
Radeon HD 7970
65%
GeForce GTX 680
66%
GeForce GTX 1050 Ti
68%
GeForce GTX 770
70%
Radeon HD 6990
71%
Radeon R9 280X
72%
GeForce GTX 590
72%
Radeon HD 7970 GHz Edition
80%
GeForce GTX 780
83%
GeForce GTX 1650
88%
Radeon RX 470
90%
Radeon R9 290
94%
Radeon RX 570
96%
Radeon R9 390
96%
Radeon R9 290X
97%
GeForce GTX 970
99%
GeForce GTX TITAN
100%
GeForce GTX 780 Ti
100%
GeForce GTX 780 Ti 6 GB
101%
Radeon R9 390X
102%
Radeon HD 7990
102%
Radeon RX 480
103%
GeForce GTX 690
109%
Radeon RX 580
111%
GeForce GTX 980
112%
Radeon R9 FURY
112%
GeForce GTX 1060 6 GB
117%
Radeon RX 590
124%
Radeon R9 295X2
124%
GeForce GTX 1660
126%
Radeon R9 FURY X
128%
GeForce GTX 980 Ti
131%
GeForce GTX TITAN X
143%
GeForce GTX 1660 Ti
143%
GeForce GTX 1070
152%
Radeon RX Vega 56
161%
GeForce GTX 1070 Ti
166%
Radeon RX Vega 64
168%
GeForce GTX 1080
168%
GeForce RTX 2060
175%
Radeon RX 5700
189%
GeForce RTX 2060 SUPER
196%
GeForce RTX 2070
200%
Radeon RX 5700 XT
203%
Radeon VII
208%
TITAN X Pascal
214%
GeForce GTX 1080 Ti
217%
GeForce RTX 2070 SUPER
230%
GeForce RTX 2080
244%
GeForce RTX 2080 SUPER
269%
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
875 MHz
Boost Clock
928 MHz
Memory Clock
1753 MHz
7012 MHz effective

Memory

Memory Size
6 GB
Memory Type
GDDR5
Memory Bus
384 bit
Bandwidth
336.6 GB/s

Render Config

Shading Units
2880
TMUs
240
ROPs
48
SMX Count
15
L1 Cache
16 KB (per SMX)
L2 Cache
1536 KB

Theoretical Performance

Pixel Rate
55.68 GPixel/s
Texture Rate
222.7 GTexel/s
FP32 (float) performance
5.345 TFLOPS
FP64 (double) performance
222.7 GFLOPS (1:24)

Board Design

Slot Width
Dual-slot
Length
10.5 inches
267 mm
TDP
250 W
Suggested PSU
600 W
Outputs
2x DVI
1x HDMI
1x DisplayPort
Power Connectors
1x 6-pin + 1x 8-pin
Board Number
P2083 SKU 30

Graphics Features

DirectX
12.0 (11_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
3.5
Shader Model
5.1

GK110B GPU Notes

L1 Cache is configurable from 16 KB up to 48 KB per SMX

GK110 chips have 5 Rasterizers each capable of 8 pixels per clock and are limited to 40 pixels per clock and because of that it can't feed all 48 ROPs when they all require data at the same time.
Luckily, additional ROPs can be used when for example MSAA is enabled (because it doesn't require additional data from rasterizers, while giving more work to ROPs).