WHAT DOES THIS WARRANTY COVER?
Any manufacturing defects or hardware component failures in your NVIDIA® branded Graphics Card that is still within warranty along with any accessories you received.
FOR HOW LONG?
Three (3) years from the date of purchase of your new Warranted Product based on product specific warranty.
WHAT WILL NVIDIA DO?
Repair, or if repair is not possible, replace your defective Warranted Product. Replacement parts and/or products may include new or refurbished parts or products and are warranted only until the expiration of the original warranty period.
WHAT DOES THIS WARRANTY NOT COVER?
Any problems that do not relate specifically to a manufacturing defect or hardware product failure, including, but not limited to, problems caused by abuse, misuse, negligence, act of God (such as flood), misapplication of service by a party other than an authorized service representative, software, shipment damages, etc.
WHAT TO DO IF YOU HAVE A PROBLEM?
If you are experiencing a problem, or if you believe that your product is defective, please contact the NVIDIA Customer Care team. We will help you troubleshoot your issue and process a replacement if it is found to be defective. NVIDIA Customer Care can be reached here, where you can search our knowledgebase for solutions to common problems or interact with our staff via the 'Ask a Question' or 'Live Chat' tabs: //nvidia.custhelp.com/cgi-bin/nvidia.cfg/php/enduser/std_alp.php
If you have registered your NVIDIA GeForce product, you can reach customer care directly with the toll free number provided to you upon registration. If you have not registered your NVIDIA GeForce product, please do so here.
LIMITATIONS OF WARRANTY
This warranty applies only to the original purchases of the Warranted Products from a retailer, mail order operation, or on-line retail store; this warranty will not extend to any person that acquires a Warranted Product on a used basis.
Warranted Product is intended for consumer end user purposes only, and is not intended for datacenter use and/or GPU cluster commercial deployments ('Enterprise Use'). Any use of Warranted Product for Enterprise Use shall void this warranty.
Your exclusive remedy, and NVIDIA's sole obligation and liability with respect to any defective product, is limited to the repair or replacement of such product as described in this warranty. NVIDIA may, at its discretion, use new or refurbished parts or units to meet the conditions of the warranty.
DISCLAIMER OF WARRANTY
EXCEPT AS EXPRESSLY PROVIDED HEREIN AND TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, NVIDIA DISCLAIMS ALL OTHER WARRANTIES WITH RESPECT TO THE PRODUCT, WHETHER EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, INCLUDING WITHOUT LIMITATION, SATISFACTORY QUALITY, COURSE OF DEALING, TRADE USAGE OR PRACTICE OR THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, OR NON-INFRINGEMENT OF THIRD PARTY RIGHTS.
SOME STATES AND JURISDICTIONS DO NOT ALLOW EXCLUSIONS OF CERTAIN IMPLIED WARRANTIES OR LIMITATIONS ON HOW LONG AN IMPLIED WARRANTY LASTS, SO SOME OF THE ABOVE LIMITATIONS MAY NOT APPLY TO YOU.
LIMITATION OF LIABILITY
IN NO EVENT SHALL NVIDIA BE LIABLE FOR INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, PUNITIVE, OR CONSEQUENTIAL DAMAGES OF ANY NATURE INCLUDING, BUT NOT LIMITED TO, LOSS OF PROFITS, DATA, REVENUE, PRODUCTION, OR USE, BUSINESS INTERRUPTION, OR PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES ARISING OUT OF OR IN CONNECTION WITH THIS LIMITED WARRANTY, OR THE USE OR PERFORMANCE OF ANY PRODUCT, WHETHER BASED ON CONTRACT OR TORT, INCLUDING NEGLIGENCE, OR ANY OTHER LEGAL THEORY, EVEN IF NVIDIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. NVIDIA'S TOTAL AGGREGATE LIABILITY FOR DAMAGES OF ANY NATURE, REGARDLESS OF FORM OF ACTION, SHALL IN NO EVENT EXCEED THE AMOUNT PAID BY YOU TO NVIDIA FOR THE PRODUCT UPON WHICH LIABILITY IS BASED. SOME STATES AND JURISDICTIONS DO NOT ALLOW FOR THE EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO THIS LIMITATION AND EXCLUSION MAY NOT APPLY TO YOU.
WITHOUT LIMITING THE GENERALITY OF THE ABOVE DISCLAIMERS, NVIDIA DOES NOT WARRANT ANY SOFTWARE PRODUCTS UNDER THESE TERMS AND CONDITIONS. WARRANTIES, IF ANY, FOR SOFTWARE ARE CONTAINED IN THE APPLICABLE LICENSE AGREEMENT WHICH ACCOMPANIES THE WARRANTED PRODUCTS.
NVIDIA RESERVES THE RIGHT TO CHANGE ITS WARRANTIES AT ANY TIME, IN ITS SOLE DISCRETION WITHOUT PRIOR NOTICE WITH RESPECT TO FUTURE SALES AND DELIVERIES.
GOVERNING LAW AND YOUR RIGHTS
This warranty gives you specific legal rights. You may also have other rights which vary from state to state, and jurisdiction to jurisdiction. You hereby agree to all terms of this warranty in the English language. The United Nations Convention on Contracts for the International Sale of Goods does not apply to this warranty and is strictly excluded. This warranty and all disputes that may arise from it shall be governed by the laws of the state of Delaware in the United States. You hereby consent to the personal jurisdiction of the state and federal courts located in Santa Clara County, California, for any lawsuit filed there arising from or related to this warranty.
Any manufacturing defects or hardware component failures in your NVIDIA® branded Graphics Card that is still within warranty along with any accessories you received.
FOR HOW LONG?
Three (3) years from the date of purchase of your new Warranted Product based on product specific warranty.
WHAT WILL NVIDIA DO?
Repair, or if repair is not possible, replace your defective Warranted Product. Replacement parts and/or products may include new or refurbished parts or products and are warranted only until the expiration of the original warranty period.
WHAT DOES THIS WARRANTY NOT COVER?
Any problems that do not relate specifically to a manufacturing defect or hardware product failure, including, but not limited to, problems caused by abuse, misuse, negligence, act of God (such as flood), misapplication of service by a party other than an authorized service representative, software, shipment damages, etc.
WHAT TO DO IF YOU HAVE A PROBLEM?
If you are experiencing a problem, or if you believe that your product is defective, please contact the NVIDIA Customer Care team. We will help you troubleshoot your issue and process a replacement if it is found to be defective. NVIDIA Customer Care can be reached here, where you can search our knowledgebase for solutions to common problems or interact with our staff via the 'Ask a Question' or 'Live Chat' tabs: //nvidia.custhelp.com/cgi-bin/nvidia.cfg/php/enduser/std_alp.php
If you have registered your NVIDIA GeForce product, you can reach customer care directly with the toll free number provided to you upon registration. If you have not registered your NVIDIA GeForce product, please do so here.
LIMITATIONS OF WARRANTY
This warranty applies only to the original purchases of the Warranted Products from a retailer, mail order operation, or on-line retail store; this warranty will not extend to any person that acquires a Warranted Product on a used basis.
Warranted Product is intended for consumer end user purposes only, and is not intended for datacenter use and/or GPU cluster commercial deployments ('Enterprise Use'). Any use of Warranted Product for Enterprise Use shall void this warranty.
Your exclusive remedy, and NVIDIA's sole obligation and liability with respect to any defective product, is limited to the repair or replacement of such product as described in this warranty. NVIDIA may, at its discretion, use new or refurbished parts or units to meet the conditions of the warranty.
DISCLAIMER OF WARRANTY
EXCEPT AS EXPRESSLY PROVIDED HEREIN AND TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, NVIDIA DISCLAIMS ALL OTHER WARRANTIES WITH RESPECT TO THE PRODUCT, WHETHER EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, INCLUDING WITHOUT LIMITATION, SATISFACTORY QUALITY, COURSE OF DEALING, TRADE USAGE OR PRACTICE OR THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, OR NON-INFRINGEMENT OF THIRD PARTY RIGHTS.
SOME STATES AND JURISDICTIONS DO NOT ALLOW EXCLUSIONS OF CERTAIN IMPLIED WARRANTIES OR LIMITATIONS ON HOW LONG AN IMPLIED WARRANTY LASTS, SO SOME OF THE ABOVE LIMITATIONS MAY NOT APPLY TO YOU.
LIMITATION OF LIABILITY
IN NO EVENT SHALL NVIDIA BE LIABLE FOR INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, PUNITIVE, OR CONSEQUENTIAL DAMAGES OF ANY NATURE INCLUDING, BUT NOT LIMITED TO, LOSS OF PROFITS, DATA, REVENUE, PRODUCTION, OR USE, BUSINESS INTERRUPTION, OR PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES ARISING OUT OF OR IN CONNECTION WITH THIS LIMITED WARRANTY, OR THE USE OR PERFORMANCE OF ANY PRODUCT, WHETHER BASED ON CONTRACT OR TORT, INCLUDING NEGLIGENCE, OR ANY OTHER LEGAL THEORY, EVEN IF NVIDIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. NVIDIA'S TOTAL AGGREGATE LIABILITY FOR DAMAGES OF ANY NATURE, REGARDLESS OF FORM OF ACTION, SHALL IN NO EVENT EXCEED THE AMOUNT PAID BY YOU TO NVIDIA FOR THE PRODUCT UPON WHICH LIABILITY IS BASED. SOME STATES AND JURISDICTIONS DO NOT ALLOW FOR THE EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO THIS LIMITATION AND EXCLUSION MAY NOT APPLY TO YOU.
WITHOUT LIMITING THE GENERALITY OF THE ABOVE DISCLAIMERS, NVIDIA DOES NOT WARRANT ANY SOFTWARE PRODUCTS UNDER THESE TERMS AND CONDITIONS. WARRANTIES, IF ANY, FOR SOFTWARE ARE CONTAINED IN THE APPLICABLE LICENSE AGREEMENT WHICH ACCOMPANIES THE WARRANTED PRODUCTS.
NVIDIA RESERVES THE RIGHT TO CHANGE ITS WARRANTIES AT ANY TIME, IN ITS SOLE DISCRETION WITHOUT PRIOR NOTICE WITH RESPECT TO FUTURE SALES AND DELIVERIES.
GOVERNING LAW AND YOUR RIGHTS
This warranty gives you specific legal rights. You may also have other rights which vary from state to state, and jurisdiction to jurisdiction. You hereby agree to all terms of this warranty in the English language. The United Nations Convention on Contracts for the International Sale of Goods does not apply to this warranty and is strictly excluded. This warranty and all disputes that may arise from it shall be governed by the laws of the state of Delaware in the United States. You hereby consent to the personal jurisdiction of the state and federal courts located in Santa Clara County, California, for any lawsuit filed there arising from or related to this warranty.
This Warranty was last updated on July 19, 2016. For purchases of Warranted Products made prior to July 19, 2016, the previous Warranty terms will apply and can be found here.
Sep 03, 2010 Is there a program / software that can determine or display my video card's Serial Number??? I'm trying to avoid 90 minutes to open the case and take out the card. It's a EVGA Nvidia 9800 GTX+ video card. How can I connect SHIELD Android TV to the SHIELD Remote or Controller? Voluntary Recall of European plug heads for NVIDIA SHIELD AC Wall Adapters.
Active12 days ago
I'm looking for a command that would give me the same info as:
Except for the GPU (type of the chip and memory, frequency).
user2413user24134,37913 gold badges43 silver badges68 bronze badges
20 Answers
That type of information is non-standard, and the tools you will use to gather it vary widely.
The command
glxinfo
will give you all available OpenGL information for the graphics processor, including its vendor name, if the drivers are correctly installed.To get clock speed information, there is no standard tool.
- For ATI/AMD GPUs,
aticonfig --odgc
will fetch the clock rates, andaticonfig --odgt
will fetch the temperature data. - For NVIDIA GPUs, the
nvclock
program will fetch the same information.
I am not aware of an equivalent tool for the open source drivers or for Intel or other GPUs.
Other information on the hardware can be fetched from the
greyfadegreyfadelspci
and lshw
tools.1,4111 gold badge12 silver badges7 bronze badges
I do not know of a direct equivalent, but lshw should give you the info you want, try:
(it also works without
sudo
but the info may be less complete/accurate)You can also install the package
Marcel StimbergMarcel Stimberglshw-gtk
to get a GUI.28.3k7 gold badges41 silver badges44 bronze badges
A blog post focusing on work done on the command-line is here:
Find out the device ID:
You can then use this output with
lspci
again, forming two nested commandsIf you have more than 1 GPU card, try this equivalent command instead:
lspci | grep ' VGA ' | cut -d' ' -f 1 | xargs -i lspci -v -s {}
Output from my system:
EDIT: You can avoid the
<access denied>
by launching with sudo
So,
(prefetchable) [size=64M)
indicates that I have a 64-MB NVIDIA card. However, I don't, it's rather 256 MB. Why? See below.To see how to get the most info and performance out of it, read an extremely comprehensive article on the Arch-Linux Wiki
For nvidia users, start with
(This works with the Nvidia drivers installed,but not with systems running the open-source 'nouveau' driver).
Output
This indicates that I have a 256 MB GDDR3 Graphics card.
At this time, I don't know how to get this for Intel and AMD/ATI GPUs.
knbknb2,2292 gold badges23 silver badges33 bronze badges
Run
David Foerstergoogle-chrome
and navigate to the URL about:gpu
.If chrome has figured out how to use OpenGL, you will get extremely detailing information about your GPU.29.4k13 gold badges70 silver badges116 bronze badges
Chris UhlikChris Uhlik
Because you specified a command like
cat
for CPU's this is therefore the equivalent for GPU's. Specifically for Nvidia cards. It requires no software except the Nvidia device driver to be loaded.The path here works for the cards I have. 2013 sage act download. But yours may differ as others have pointed out in the comments.
1st GPU
2nd GPU
Matt HMatt H1,5995 gold badges22 silver badges36 bronze badges
QuanlongQuanlong
clinfo
is the analogue of
glxinfo
but for OpenCL.nvidia-settings
Mixes runtime with some static info.
More details: How do I check if Ubuntu is using my NVIDIA graphics card?
Ciro Santilli 新疆改造中心法轮功六四事件Ciro Santilli 新疆改造中心法轮功六四事件12.3k5 gold badges55 silver badges59 bronze badges
I do believe the best option for this is neofetch.
This gives an output like this:
Kevin Bowen16k15 gold badges62 silver badges73 bronze badges
HaoZekeHaoZeke
I use two methods to automatically display nVidia GPU and Intel iGPU information:
- Conky dynamically displays GPU information in real time
~/.bashrc
displays GPU information each time the terminal is opened
Conky real time display
This example uses Conky to display current GPU (nVidia or Intel) stats in real time. Conky is a light weight system monitor popular among many Linux enthusiasts.
The display changes depending on if you booted after
prime-select intel
or prime-select nvidia
.Intel iGPU
- The Intel iGPU shows as
Skylake GT2 HD 530 iGPU
with current frequency - The Minimum frequency is
350
MHz and the Maximum is1050
MHz
nVidia GPU
- The nVidia GPU shows as
GeForce GTX970M
with current GPU frequency and temperature - The Driver version, P-State and BIOS version are displayed
- The GPU load, RAM use, Power Consumption and RAM frequency is displayed
Conky Code
Here is the relevant Conky script for Intel iGPU and nVidia GPU:
~/.bashrc
Terminal splash screen
This example modifies
~/.bashrc
to display information on a splash screen each time the terminal is opened or whenever you type . .bashrc
at the shell prompt.In addition to
neofetch
answered previously, there is screenfetch
which looks a lot nicer (IMO). Plus another answer mentions he doesn't know how to get iGPU listed and this does it:For details on setup see: Terminal splash screen with Weather, Calendar, Time & Sysinfo?
In summary just for the bottom section with Ubuntu display containing GPU information (second last line) use:
You'll want to put the
WinEunuuchs2Unixscreenfetch
command an the bottom of your ~/.bashrc
file to have it appear every time you open the terminal.Nvidia Gpu Serial Number 1
WinEunuuchs2Unix58.8k18 gold badges119 silver badges232 bronze badges
Just to find the basics, according to https://wiki.debian.org/NvidiaGraphicsDrivers#NVIDIA_Proprietary_Driver,
If you need more detail than that, see @knb's answer to this same question.
mightypilemightypile5001 gold badge8 silver badges11 bronze badges
This is really not that complex For model and memory, here's a 1 liner that works for every video card I've tested it on regardless of manufacturer (Intel, AMD, NVIDIA):
GPU=$(lspci | grep VGA | cut -d ':' -f3);RAM=$(cardid=$(lspci | grep VGA |cut -d ' ' -f1);lspci -v -s $cardid | grep ' prefetchable'| cut -d '=' -f2);echo $GPU $RAM
GPU= All this bit does is grab the 3rd field from 'lspci' output filtered via 'grep' for VGA which corresponds to the video chip.
RAM= All this bit does is set variable
cardid
equal to the first field of output from lspci
matching 'VGA' and feeds that as a request for -v
verbose output from lspci
for that specific -s
device, further filtering the output by grep
for the string ' prefetchable' as this contains the memory on the card itself (note the preceding space as we don't want to match 'non-prefetchable' in our output.For clock rate on Intel integrated graphics (Tested on I3 and I5)
execute the command
sudo find /sys -type f -name gt_cur* -print0 | xargs -0 cat
This dives into the /sys tree to locate the gt_cur_freq_mhzfile which on my I3 is /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_cur_freq_mhz
and prints the content. which in my case under extremely light load is 350
as in 350 MHz which corresponds to the minimum frequency found in /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_min_freq_mhz
and when running glxgears
and glmark2
results in 1050
as in 1050 MHz which corresponds to the maximum frequency found in /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_max_freq_mhz
For clock rates on nvidia cards:
nvidia-smi -stats -d procClk
corresponds to the GPU clocknvidia-smi -stats -d memClk
corresponds to the memory clock.Note: I am unable to test the above as my trusty GeForce 210 isn't supported and this works only on Kepler or newer GPUs as indicated by `nvidia-smi -stats --help'
I do not currently have any solutions for clock rate on AMD cards and do not have the hardware available for testing. I will however say that to the best of my knowledge the
Elder GeekElder Geekaticonfig
mentioned in the accepted answer no longer exists and it appears that nvclock
isn't available for anything since trusty.28.6k11 gold badges64 silver badges140 bronze badges
If you're running Ubuntu on a Chromebook with crouton, the only one of the answers that will work is going to
David Foersterchrome://gpu
in the Chrome browser. 29.4k13 gold badges70 silver badges116 bronze badges
k26drk26dr
If you would like to have simple information, you could try gpustat. It is very good and simple.
The author gives the following installation instructions:
Install from PyPI:
To install the latest version (master branch) via pip:
If you don't have root privilege, please try to install on user namespace:
pip install --user
. Note that from v0.4, gpustat.py
is no more a zero-dependency executable. However, in rare cases you'll need a single executable script (legacy), you can also try:NufaNufa
Well, this answer assumes you have a server with NVIDIA-GPUs. You have three ways:
- To get just a short gist:
nvidia-smi
- To get a detailed one :
nvidia-smi -q
. You'll get multiple screens of detailed info if you more than 1 gpu.Downloads for older operating systemsAfter the installation of an older version of the eLicenser Control Center, it is recommended to open the program and apply the 'Maintenance & Online Synchronisation' by clicking on 'Perform Maintenance Tasks' (or click on the 'Maintenance' button at the top right if not shown). Mac Mac OS X 10.9 10.10 10.11 macOS 10.12 10.13 10.14 10.15Windows Windows 7 Windows 8 Windows 10Microsoft.NET Framework 4.0 or later must be installed!September 3, 2019 35.4 MBSeptember 3, 2019 65.3 MB. Download the latest eLicenser Control CenterMost issues with Soft-eLicensers or USB-eLicensers, activation codes and licenses can easily be solved by installing the latest eLicenser Control Center.After the installation, please open the eLicenser Control Center and apply the 'Maintenance & Online Synchronisation' by clicking on 'Perform Maintenance Tasks' (or click on the 'Maintenance' button if not shown). License control center cubase 7. - Do a
ls /proc/driver/nvidia/gpus/
. It'll display the GPU-bus location as folders. Now, run the following command for each of the gpu bus locations. Fill<gpu-id>
with bus-location:cat /proc/driver/nvidia/gpus/<gpu_id>/information
Sritanu ChakrabortySritanu Chakraborty
For the Intel GMA950 (comes with EeePC in particular) you can run:
which will return '00' for 200MHz, '01' for 250MHz or '03' for 400MHz. You may be able to apply the same principle to other Intel cards.
user10872
If you have a AMD Radeon Card, you may want to run the following commands
It should report something like this
NerrveNerrve
For nvidia GPUs,
nvidia-smi
command is your friend.See man nvidia-smi
if you like to.For listing GPUs use
nvidia-smi -L
(nvidia-smi --list-gpus
),nvidia-smi -q
give information about the gpu and the running processes.MeminMemin
Use
lspci
, lspci -v
to get basic info see here.In my case for ex once I run
lspci
and I have got :DINA TAKLITDINA TAKLIT
In order to get all the information about the graphics processor, you can use the following command as specified by @greyfade.
However, if the program
glxinfo
is currently not installed, you can install it by typing:You will also have to enable the component called
universe
. Once this is done, glxinfo
will list all the specifications related to the graphics processor in that environment.Nayantara JeyarajNayantara Jeyaraj
If you're looking for only the names of the video cards on the machine, then simply use:
For some newer GPUs, this also lists the memory of each device.
kmario23kmario234521 gold badge5 silver badges17 bronze badges