Report an Error

NVIDIA NVS 810

Graphics Processor
GM107 x2
Cores
512 x2
TMUs
32 x2
ROPs
16 x2
Memory Size
2 GB x2
Memory Type
DDR3
Bus Width
64 bit x2
The NVS 810 is a professional graphics card by NVIDIA, launched in November 2015. Built on the 28 nm process, and based on the GM107 graphics processor, the card supports DirectX 12.0. The GM107 graphics processor is an average sized chip with a die area of 148 mm² and 1,870 million transistors. Unlike the fully unlocked GeForce GTX 750 Ti, which uses the same GPU but has all 640 shaders enabled, NVIDIA has disabled some shading units on the NVS 810 to reach the product's target shader count. NVS 810 combines two graphics processors to increase performance. It features 512 shading units, 32 texture mapping units and 16 ROPs per GPU. NVIDIA has placed 4,096 MB DDR3 memory on the card, which are connected using a 64-bit memory interface per GPU (each GPU manages 2,048 MB). The GPU is operating at a frequency of 902 MHz, which can be boosted up to 1033 MHz, memory is running at 900 MHz.
Being a single-slot card, the NVIDIA NVS 810 does not require any additional power connector, its power draw is rated at 68 W maximum. Display outputs include: 8x mini-DisplayPort. NVS 810 is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 198 mm in length, and features a single-slot cooling solution.

Graphics Processor

GPU Name
GM107
Architecture
Maxwell
Foundry
TSMC
Process Size
28 nm
Transistors
1,870 million
Die Size
148 mm²

Graphics Card

Release Date
Nov 4th, 2015
Generation
NVS
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

7%
GeForce 210
9%
GeForce 9400 GT
11%
Radeon HD 4550
15%
Radeon HD 5450
17%
Radeon HD 6450
18%
GeForce GT 520
22%
GeForce GT 220
29%
GeForce GT 430
30%
Radeon HD 5570
32%
Radeon HD 4670
34%
GeForce GT 440
35%
GeForce GT 240
40%
GeForce 9600 GT
42%
Radeon HD 5670
45%
GeForce GT 640
47%
GeForce 9800 GT
49%
Radeon HD 6670
50%
Radeon HD 4830
54%
Radeon HD 4770
57%
Radeon HD 4850
58%
GeForce GTS 250
60%
GeForce GTS 450
62%
Radeon HD 5750
70%
Radeon HD 7750
71%
Radeon HD 5770
72%
GeForce GTX 260
73%
Radeon HD 4870
73%
Radeon Vega 8
74%
GeForce GTX 550 Ti
75%
GeForce GTX 650
79%
Radeon HD 5830
83%
Radeon HD 6790
85%
Radeon HD 4890
88%
GeForce GTX 460
88%
Radeon RX Vega 11
89%
GeForce GT 1030
90%
GeForce GTX 275
90%
Radeon HD 7770 GHz Edition
90%
GeForce GTX 280
92%
GeForce GTX 465
97%
Radeon HD 6850
99%
GeForce GTX 285
100%
NVS 810
106%
Radeon HD 5850
108%
GeForce GTX 650 Ti
108%
Radeon HD 7790
112%
Radeon RX 550
112%
GeForce GTX 470
117%
Radeon HD 6870
124%
Radeon HD 5870
128%
GeForce GTX 560 Ti
129%
Radeon HD 4870 X2
131%
GeForce GTX 750 Ti
132%
Radeon HD 6950
137%
GeForce GTX 295
138%
GeForce GTX 650 Ti Boost
139%
Radeon HD 7850
142%
GeForce GTX 480
148%
Radeon HD 6970
151%
Radeon R7 265
153%
Radeon RX 460
153%
Radeon R7 370
154%
GeForce GTX 660
155%
GeForce GTX 570
157%
Radeon RX 560
167%
GeForce GTX 950
168%
Radeon HD 7870 GHz Edition
172%
Radeon R9 270X
174%
GeForce GTX 660 Ti
175%
GeForce GTX 580
177%
GeForce GTX 1050
177%
Radeon HD 7950
181%
Radeon HD 5970
186%
GeForce GTX 760
200%
GeForce GTX 670
205%
GeForce GTX 960
210%
Radeon R9 380
211%
Radeon R9 285
214%
Radeon HD 7970
216%
GeForce GTX 680
221%
GeForce GTX 1050 Ti
227%
GeForce GTX 770
232%
Radeon HD 6990
237%
Radeon R9 280X
241%
GeForce GTX 590
241%
Radeon HD 7970 GHz Edition
267%
GeForce GTX 780
276%
GeForce GTX 1650
294%
Radeon RX 470
298%
Radeon R9 290
314%
Radeon RX 570
318%
Radeon R9 390
319%
Radeon R9 290X
324%
GeForce GTX 970
328%
GeForce GTX TITAN
332%
GeForce GTX 780 Ti
337%
Radeon R9 390X
339%
Radeon HD 7990
340%
Radeon RX 480
343%
GeForce GTX 690
361%
Radeon RX 580
369%
GeForce GTX 980
374%
Radeon R9 FURY
374%
GeForce GTX 1060 6 GB
390%
Radeon RX 590
411%
Radeon R9 295X2
413%
GeForce GTX 1660
418%
Radeon R9 FURY X
425%
GeForce GTX 980 Ti
436%
GeForce GTX TITAN X
475%
GeForce GTX 1660 Ti
475%
GeForce GTX 1070
505%
Radeon RX Vega 56
536%
GeForce GTX 1070 Ti
551%
Radeon RX Vega 64
559%
GeForce GTX 1080
559%
GeForce RTX 2060
582%
Radeon RX 5700
628%
GeForce RTX 2060 SUPER
651%
GeForce RTX 2070
666%
Radeon RX 5700 XT
674%
Radeon VII
691%
TITAN X Pascal
712%
GeForce GTX 1080 Ti
720%
GeForce RTX 2070 SUPER
766%
GeForce RTX 2080
896%
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
902 MHz
Boost Clock
1033 MHz
Memory Clock
900 MHz
1800 MHz effective

Memory

Memory Size
2 GB
Memory Type
DDR3
Memory Bus
64 bit
Bandwidth
14.40 GB/s

Render Config

Shading Units
512
TMUs
32
ROPs
16
SMM Count
4
L1 Cache
64 KB (per SMM)
L2 Cache
1024 KB

Theoretical Performance

Pixel Rate
16.53 GPixel/s
Texture Rate
33.06 GTexel/s
FP32 (float) performance
1,058 GFLOPS
FP64 (double) performance
33.06 GFLOPS (1:32)

Board Design

Slot Width
Single-slot
Length
7.8 inches
198 mm
TDP
68 W
Outputs
8x mini-DisplayPort
Power Connectors
None
Board Number
P2010

Graphics Features

DirectX
12.0 (11_0)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
5.0
Shader Model
5.1