Report an Error

NVIDIA GRID K100

Graphics Processor
GK107
Cores
192
TMUs
16
ROPs
16
Memory Size
256 MB
Memory Type
DDR3
Bus Width
128 bit
The GRID K100 was an entry-level professional graphics card by NVIDIA, launched in June 2013. Built on the 28 nm process, and based on the GK107 graphics processor, the card supports DirectX 12.0. The GK107 graphics processor is an average sized chip with a die area of 118 mm² and 1,270 million transistors. Unlike the fully unlocked GeForce GT 640 OEM, which uses the same GPU but has all 384 shaders enabled, NVIDIA has disabled some shading units on the GRID K100 to reach the product's target shader count. It features 192 shading units, 16 texture mapping units and 16 ROPs. NVIDIA has placed 256 MB DDR3 memory on the card, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 850 MHz, memory is running at 891 MHz.
Being a dual-slot card, its power draw is rated at 130 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. GRID K100 is connected to the rest of the system using a PCI-Express 3.0 x16 interface. Its price at launch was 63 US Dollars.

Graphics Processor

GPU Name
GK107
Architecture
Kepler
Foundry
TSMC
Process Size
28 nm
Transistors
1,270 million
Die Size
118 mm²

Graphics Card

Release Date
Jun 28th, 2013
Generation
GRID K1
Production
End-of-life
Launch Price
63 USD
Bus Interface
PCIe 3.0 x16

Relative Performance

34%
GeForce 210
43%
GeForce 9400 GT
53%
Radeon HD 4550
68%
Radeon HD 5450
80%
Radeon HD 6450
85%
GeForce GT 520
100%
GRID K100
105%
GeForce GT 220
137%
GeForce GT 430
139%
Radeon HD 5570
151%
Radeon HD 4670
159%
GeForce GT 440
162%
GeForce GT 240
186%
GeForce 9600 GT
198%
Radeon HD 5670
212%
GeForce GT 640
219%
GeForce 9800 GT
228%
Radeon HD 6670
236%
Radeon HD 4830
251%
Radeon HD 4770
265%
Radeon HD 4850
271%
GeForce GTS 250
279%
GeForce GTS 450
289%
Radeon HD 5750
330%
Radeon HD 7750
332%
Radeon HD 5770
338%
GeForce GTX 260
343%
Radeon HD 4870
343%
Radeon Vega 8
347%
GeForce GTX 550 Ti
350%
GeForce GTX 650
370%
Radeon HD 5830
389%
Radeon HD 6790
396%
Radeon HD 4890
410%
GeForce GTX 460
414%
Radeon RX Vega 11
418%
GeForce GT 1030
422%
GeForce GTX 275
423%
Radeon HD 7770 GHz Edition
424%
GeForce GTX 280
432%
GeForce GTX 465
453%
Radeon HD 6850
461%
GeForce GTX 285
495%
Radeon HD 5850
504%
GeForce GTX 650 Ti
504%
Radeon HD 7790
525%
Radeon RX 550
527%
GeForce GTX 470
546%
Radeon HD 6870
582%
Radeon HD 5870
600%
GeForce GTX 560 Ti
604%
Radeon HD 4870 X2
615%
GeForce GTX 750 Ti
618%
Radeon HD 6950
639%
GeForce GTX 295
647%
GeForce GTX 650 Ti Boost
652%
Radeon HD 7850
663%
GeForce GTX 480
694%
Radeon HD 6970
707%
Radeon R7 265
718%
Radeon RX 460
719%
Radeon R7 370
721%
GeForce GTX 660
723%
GeForce GTX 570
735%
Radeon RX 560
781%
GeForce GTX 950
788%
Radeon HD 7870 GHz Edition
807%
Radeon R9 270X
817%
GeForce GTX 660 Ti
821%
GeForce GTX 580
827%
GeForce GTX 1050
829%
Radeon HD 7950
845%
Radeon HD 5970
869%
GeForce GTX 760
935%
GeForce GTX 670
960%
GeForce GTX 960
984%
Radeon R9 380
990%
Radeon R9 285
1000%
Radeon HD 7970
1010%
GeForce GTX 680
1034%
GeForce GTX 1050 Ti
1061%
GeForce GTX 770
1086%
Radeon HD 6990
1111%
Radeon R9 280X
1127%
GeForce GTX 590
1128%
Radeon HD 7970 GHz Edition
1250%
GeForce GTX 780
1294%
GeForce GTX 1650
1375%
Radeon RX 470
1394%
Radeon R9 290
1469%
Radeon RX 570
1487%
Radeon R9 390
1495%
Radeon R9 290X
1515%
GeForce GTX 970
1535%
GeForce GTX TITAN
1556%
GeForce GTX 780 Ti
1578%
Radeon R9 390X
1585%
Radeon HD 7990
1593%
Radeon RX 480
1606%
GeForce GTX 690
1649%
GeForce GTX 1060 6 GB
1672%
Radeon RX 5500
1692%
Radeon RX 580
1727%
GeForce GTX 980
1742%
GeForce GTX 1650 SUPER
1750%
Radeon R9 FURY
1828%
Radeon RX 590
1925%
Radeon R9 295X2
1935%
GeForce GTX 1660
1958%
Radeon R9 FURY X
1991%
GeForce GTX 980 Ti
2043%
GeForce GTX TITAN X
2174%
GeForce GTX 1660 SUPER
2222%
GeForce GTX 1660 Ti
2222%
GeForce GTX 1070
2365%
Radeon RX Vega 56
2509%
GeForce GTX 1070 Ti
2580%
Radeon RX Vega 64
2616%
GeForce RTX 2060
2616%
GeForce GTX 1080
2724%
Radeon RX 5700
2939%
GeForce RTX 2060 SUPER
3046%
GeForce RTX 2070
3118%
Radeon RX 5700 XT
3154%
Radeon VII
3235%
TITAN X Pascal
3333%
GeForce GTX 1080 Ti
3369%
GeForce RTX 2070 SUPER
3584%
GeForce RTX 2080
3799%
GeForce RTX 2080 SUPER
4193%
GeForce RTX 2080 Ti
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
850 MHz
Memory Clock
891 MHz
1782 MHz effective

Memory

Memory Size
256 MB
Memory Type
DDR3
Memory Bus
128 bit
Bandwidth
28.51 GB/s

Render Config

Shading Units
192
TMUs
16
ROPs
16
SMX Count
1
L1 Cache
16 KB (per SMX)
L2 Cache
256 KB

Theoretical Performance

Pixel Rate
3.400 GPixel/s
Texture Rate
13.60 GTexel/s
FP32 (float) performance
326.4 GFLOPS
FP64 (double) performance
13.60 GFLOPS (1:24)

Board Design

Slot Width
Dual-slot
TDP
130 W
Suggested PSU
350 W
Outputs
No outputs

Graphics Features

DirectX
12.0 (11_0)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
3.0
Shader Model
5.1

Card Notes

Virtual GPU Inside a GRID K1 Card

GK107 GPU Notes

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