Report an Error

NVIDIA GeForce 920MX

Graphics Processor
GM108S
Cores
256
TMUs
24
ROPs
8
Memory Size
2 GB
Memory Type
DDR3
Bus Width
64 bit
GPU Chip
GPU
The GeForce 920MX was a mobile graphics chip by NVIDIA, launched on March 25th, 2016. Built on the 28 nm process, and based on the GM108S graphics processor, in its N16V-GMR1-S-A2 variant, the chip supports DirectX 12. Even though it supports DirectX 12, the feature level is only 11_0, which can be problematic with newer DirectX 12 titles. The GM108S graphics processor is a relatively small chip with a die area of only 77 mm² and 1,020 million transistors. Unlike the fully unlocked GeForce 840M, which uses the same GPU but has all 384 shaders enabled, NVIDIA has disabled some shading units on the GeForce 920MX to reach the product's target shader count. It features 256 shading units, 24 texture mapping units, and 8 ROPs. NVIDIA has paired 2,048 MB DDR3 memory with the GeForce 920MX, which are connected using a 64-bit memory interface. The GPU is operating at a frequency of 965 MHz, which can be boosted up to 993 MHz, memory is running at 900 MHz.
Being a mxm module card, the NVIDIA GeForce 920MX does not require any additional power connector, its power draw is rated at 16 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Rather it is intended for use in laptop/notebooks and will use the output of the host mobile device. GeForce 920MX is connected to the rest of the system using a PCI-Express 3.0 x8 interface.

Graphics Processor

GPU Name
GM108S
GPU Variant
N16V-GMR1-S-A2
Architecture
Maxwell
Foundry
TSMC
Process Size
28 nm
Transistors
1,020 million
Density
13.2M / mm²
Die Size
77 mm²
Chip Package
FCBGA-595

Mobile Graphics

Release Date
Mar 25th, 2016
Generation
GeForce 900M
Predecessor
GeForce 800M
Successor
GeForce 10 Mobile
Production
End-of-life
Bus Interface
PCIe 3.0 x8

Relative Performance

GeForce 210
15%
GeForce 9400 GT
19%
Radeon HD 4550
24%
Radeon HD 5450
30%
Radeon HD 6450
36%
GeForce GT 520
38%
GeForce GT 220
47%
GeForce GT 430
61%
Radeon HD 5570
62%
Radeon HD 4670
67%
GeForce GT 440
71%
GeForce GT 240
72%
GeForce 9600 GT
83%
Radeon HD 5670
88%
GeForce GT 640
94%
GeForce 9800 GT
98%
GeForce 920MX
100%
Radeon HD 6670
101%
Radeon HD 4830
105%
Radeon HD 4770
112%
Radeon HD 4850
118%
GeForce GTS 250
120%
GeForce GTS 450
124%
Radeon HD 5750
128%
Radeon HD 7750
147%
Radeon HD 5770
148%
GeForce GTX 260
150%
Radeon HD 4870
152%
Radeon Vega 8
153%
GeForce GTX 550 Ti
154%
GeForce GTX 650
156%
Radeon HD 5830
164%
Radeon HD 6790
173%
Radeon HD 4890
176%
GeForce GTX 460
182%
Radeon RX Vega 11
184%
GeForce GT 1030
186%
GeForce GTX 275
187%
Radeon HD 7770 GHz Edition
188%
GeForce GTX 280
188%
GeForce GTX 465
192%
Radeon HD 6850
201%
GeForce GTX 285
205%
Radeon HD 5850
220%
GeForce GTX 650 Ti
224%
Radeon HD 7790
224%
Radeon RX 550
234%
GeForce GTX 470
234%
Radeon HD 6870
243%
Radeon HD 5870
259%
GeForce GTX 560 Ti
267%
Radeon HD 4870 X2
268%
GeForce GTX 750 Ti
273%
Radeon HD 6950
275%
GeForce GTX 295
284%
GeForce GTX 650 Ti Boost
288%
Radeon HD 7850
290%
GeForce GTX 480
295%
Radeon HD 6970
308%
Radeon R7 265
314%
Radeon RX 460
319%
Radeon R7 370
319%
GeForce GTX 660
321%
GeForce GTX 570
322%
Radeon RX 560
327%
GeForce GTX 950
347%
Radeon HD 7870 GHz Edition
350%
Radeon R9 270X
359%
GeForce GTX 660 Ti
363%
GeForce GTX 580
365%
GeForce GTX 1050
368%
Radeon HD 7950
369%
GeForce GTX 1630
375%
Radeon HD 5970
376%
GeForce GTX 760
386%
GeForce GTX 670
416%
GeForce GTX 960
427%
Radeon R9 380
437%
Radeon R9 285
440%
Radeon HD 7970
445%
GeForce GTX 680
449%
GeForce GTX 1050 Ti
460%
GeForce GTX 770
472%
Radeon HD 6990
483%
Radeon R9 280X
494%
GeForce GTX 590
501%
Radeon HD 7970 GHz Edition
501%
GeForce GTX 780
555%
Arc A380
556%
Radeon RX 6400
564%
GeForce GTX 1650
575%
Radeon RX 470
611%
Radeon R9 290
620%
Radeon RX 570
653%
Radeon R9 390
661%
Radeon R9 290X
665%
GeForce GTX 970
674%
GeForce GTX TITAN
682%
GeForce GTX 780 Ti
692%
Radeon R9 390X
701%
Radeon HD 7990
705%
Radeon RX 480
708%
GeForce GTX 690
714%
GeForce GTX 1060 6 GB
733%
Radeon RX 5500 OEM
743%
Radeon RX 580
752%
Radeon RX 5500 XT
758%
Radeon RX 6500 XT
765%
GeForce GTX 980
768%
GeForce GTX 1650 SUPER
775%
Radeon R9 FURY
778%
Radeon RX 590
812%
Radeon R9 295X2
856%
GeForce GTX 1660
860%
Radeon R9 FURY X
870%
GeForce GTX 980 Ti
885%
GeForce GTX TITAN X
908%
GeForce GTX 1660 SUPER
935%
GeForce GTX 1070
988%
GeForce GTX 1660 Ti
988%
GeForce RTX 3050 8 GB
1004%
Radeon RX Vega 56
1051%
GeForce GTX 1070 Ti
1115%
Radeon RX 5600 XT
1132%
Radeon RX Vega 64
1147%
GeForce GTX 1080
1163%
GeForce RTX 2060
1163%
Radeon RX 5700
1211%
Arc A580
1213%
Radeon RX 6600
1264%
GeForce RTX 2060 SUPER
1306%
GeForce RTX 2070
1323%
Radeon RX 5700 XT
1324%
GeForce RTX 3060 12 GB
1350%
Arc A750
1394%
Radeon VII
1402%
TITAN X Pascal
1438%
Radeon RX 6600 XT
1453%
GeForce GTX 1080 Ti
1481%
Arc A770
1496%
GeForce RTX 2070 SUPER
1497%
Radeon RX 6650 XT
1575%
Radeon RX 7600
1593%
GeForce RTX 4060
1600%
GeForce RTX 2080
1611%
Radeon RX 7600 XT
1643%
GeForce RTX 2080 SUPER
1689%
GeForce RTX 3060 Ti
1730%
Radeon RX 6700 XT
1791%
Radeon RX 6750 XT
1901%
GeForce RTX 4060 Ti 8 GB
1921%
GeForce RTX 2080 Ti
1936%
GeForce RTX 3070
2026%
GeForce RTX 3070 Ti
2168%
Radeon RX 7700 XT
2190%
Radeon RX 6800
2233%
GeForce RTX 4070
2474%
Radeon RX 6800 XT
2536%
GeForce RTX 3080
2633%
Radeon RX 7800 XT
2659%
Radeon RX 6900 XT
2733%
GeForce RTX 4070 SUPER
2870%
Radeon RX 7900 GRE
2925%
GeForce RTX 3080 Ti
2949%
Radeon RX 6950 XT
2953%
GeForce RTX 3090
3005%
GeForce RTX 4070 Ti
3080%
GeForce RTX 4070 Ti SUPER
3365%
Radeon RX 7900 XT
3456%
GeForce RTX 3090 Ti
3486%
GeForce RTX 4080
3913%
GeForce RTX 4080 SUPER
3972%
Radeon RX 7900 XTX
4009%
GeForce RTX 4090
4916%
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
965 MHz
Boost Clock
993 MHz
Memory Clock
900 MHz
1800 Mbps effective

Memory

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

Render Config

Shading Units
256
TMUs
24
ROPs
8
SMM Count
2
L1 Cache
64 KB (per SMM)
L2 Cache
1024 KB

Theoretical Performance

Pixel Rate
7.944 GPixel/s
Texture Rate
23.83 GTexel/s
FP32 (float)
508.4 GFLOPS
FP64 (double)
15.89 GFLOPS (1:32)

Board Design

Slot Width
MXM Module
TDP
16 W
Outputs
Portable Device Dependent
Power Connectors
None

Graphics Features

DirectX
12 (11_0)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
5.0
Shader Model
6.7 (5.1)

GM108S GPU Notes

NVENC: No Support
NVDEC: No Support
PureVideo HD: VP6
VDPAU: Feature Set E

Devices based on this design (3)

Name GPU Clock Boost Clock Memory Clock Other Changes
965 MHz 993 MHz 900 MHz
1004 MHz 993 MHz 900 MHz
939 MHz 980 MHz 1253 MHz GDDR5
Apr 18th, 2024 03:08 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts