User:Terasail/sandbox/article: Difference between revisions
Appearance
< User:Terasail | sandbox
Content deleted Content added
→GeForce 600 series: Convert to overview table |
→GeForce 700 series: Convert to overview table |
||
Line 831: | Line 831: | ||
* Improve [[Nvidia NVENC|NVENC]] |
* Improve [[Nvidia NVENC|NVENC]] |
||
{|class="wikitable" style="text-align:center;" |
|||
!Model name |
|||
{| class="wikitable" style="font-size: 80%; text-align: center;" |
|||
!Launch date |
|||
!TDP (Watts) |
|||
!Release Price (USD) |
|||
|- |
|- |
||
!GeForce GT 705 |
|||
! rowspan="2" | Model |
|||
|rowspan=2|March 27, 2014 |
|||
|29 |
|||
! rowspan="2" | [[Code name]] |
|||
|OEM |
|||
! rowspan="2" | Fab ([[Nanometer|nm]]) |
|||
! rowspan="2" | Transistors (million) |
|||
! rowspan="2" | Die size (mm<sup>2</sup>) |
|||
! rowspan="2" | [[Computer bus|Bus]] [[I/O interface|interface]] |
|||
! rowspan="2" | SMX count |
|||
! rowspan="2" | Core config{{efn|name=geforce 700 1|[[Unified shader model|Unified shaders]]: [[texture mapping unit]]s: [[render output unit]]s}} |
|||
! colspan="4" | Clock rate |
|||
! colspan="2" | [[Fillrate]] |
|||
! colspan="4" | Memory configuration |
|||
! colspan="4" | Supported [[Application programming interface|API]] version |
|||
! colspan="2" | Processing power ([[GFLOPS]]){{efn|name=geforce 700 9|To calculate the processing power see [[Maxwell (microarchitecture)#Performance]], or [[Kepler (microarchitecture)#Performance]].}} |
|||
! rowspan="2" | [[Thermal design power|TDP]] (Watts) |
|||
! rowspan="2" | Release Price (USD) |
|||
|- |
|- |
||
!rowspan=2|GeForce GT 710 |
|||
! Base ([[Hertz|MHz]]) |
|||
| |
|||
! Average Boost ([[Hertz|MHz]]) |
|||
|OEM |
|||
! Max Boost{{efn|name=geforce 700 2|Max Boost depends on ASIC quality. For example, some GTX TITAN with over 80% ASIC quality can hit 1019 MHz by default, lower ASIC quality will be 1006 MHz or 993 MHz.}} ([[Hertz|MHz]]) |
|||
! Memory ([[Hertz|MHz]]) |
|||
! Pixel ([[Pixel|GP]]/s) |
|||
! Texture ([[Texel (graphics)|GT]]/s) |
|||
! Size ([[Megabyte|MB]]) |
|||
! Bandwidth ([[Gigabyte|GB]]/s) |
|||
! DRAM type |
|||
! Bus width ([[bit]]) |
|||
! [[Vulkan (API)|Vulkan]]{{efn|name=geforce 700 11|Maxwell supports Vulkan version 1.3, while Kepler only support Vulkan version 1.2, Fermi does not support the Vulkan API at all.<ref name="vulkandrv" />}} |
|||
! [[Direct3D]]{{efn|name=geforce 700 3|Kepler supports some optional 11.1 features on [[Direct3D feature level|feature level]] 11_0 through the Direct3D 11.1 API, however Nvidia did not enable four non-gaming features to qualify Kepler for level 11_1.<ref>{{cite web |url=http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html |title=Nvidia Kepler not fully compliant with Direct3D 11.1 |website=Guru3d.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151222113454/http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html |archive-date=2015-12-22 |url-status=live }}</ref><ref>[http://www.brightsideofnews.com/news/2012/11/21/nvidia-doesnt-fully-support-Direct3D-111-with-kepler-gpus2c-bute280a6.aspx Nvidia Doesn't Fully Support DirectX 11.1 with Kepler GPUs, But... - BrightSideOfNews.com] {{webarchive |url=https://web.archive.org/web/20130903174514/http://www.brightsideofnews.com/news/2012/11/21/nvidia-doesnt-fully-support-directx-111-with-kepler-gpus2c-bute280a6.aspx |date=September 3, 2013 }}</ref>}} |
|||
! [[OpenGL]] |
|||
! [[OpenCL]] |
|||
! [[Single precision floating-point format|Single precision]] |
|||
! [[Double precision floating-point format|Double precision]] |
|||
|- |
|- |
||
|January 26, 2016 |
|||
! style="text-align:left;" | GeForce GT 705<ref>{{cite web |url=http://www.techpowerup.com/gpudb/2578/geforce-gt-705.html |title=Nvidia GeForce GT 705 {{pipe}} techPowerUp GPU Database |website=Techpowerup.com |access-date=2015-12-11 |archive-url=https://archive.today/20140615091732/http://www.techpowerup.com/gpudb/2578/geforce-gt-705.html |archive-date=2014-06-15 |url-status=live }}</ref>{{efn|name=geforce 700 4|The GeForce GT 705 (OEM) is a rebranded GeForce GT 610, which itself is a rebranded GeForce GT 520.}} |
|||
| |
|rowspan=2|19 |
||
|$35–45 |
|||
| GF119-300-A1 |
|||
| [[TSMC]] 40 nm |
|||
| 292 |
|||
| 79 |
|||
| PCIe 2.0 x16 |
|||
| rowspan="4" | 1 |
|||
| 48:8:4 |
|||
| 810 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 898<br />(1796) |
|||
| 3.24 |
|||
| 6.5 |
|||
| 512<br />1024 |
|||
| rowspan="2" | 14.4 |
|||
| rowspan="2" | DDR3 |
|||
| 64 |
|||
| n/a |
|||
| rowspan="21" | 12 |
|||
| rowspan="20" | 4.6 |
|||
| 1.1 |
|||
| 155.5 |
|||
| 19.4 |
|||
| 29 |
|||
| rowspan="2" | OEM |
|||
|- |
|- |
||
!GeForce GT 720 |
|||
! rowspan="2" style="text-align:left;" | GeForce GT 710<ref>{{cite web |url=http://www.techpowerup.com/gpudb/1990/geforce-gt-710.html |title=Nvidia GeForce GT 710 {{pipe}} techPowerUp GPU Database |website=Techpowerup.com |access-date=2015-12-11 |archive-url=https://archive.today/20140615091722/http://www.techpowerup.com/gpudb/1990/geforce-gt-710.html |archive-date=2014-06-15 |url-status=live }}</ref> |
|||
|March 27, 2014 |
|||
| GK208-301-A1 |
|||
|$49–59 |
|||
| rowspan="5" | TSMC [[28 nm]] |
|||
| rowspan="5" | 1020 |
|||
| rowspan="5" | 79 |
|||
| PCIe 2.0 x8 |
|||
| 192:16:8 |
|||
| 823 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 900 (1800) |
|||
| 6.6 |
|||
| 13.2 |
|||
| 512 |
|||
| rowspan="5" | 64 |
|||
| rowspan="5" | 1.2 |
|||
| rowspan="5" | 1.2 |
|||
| 316.0 |
|||
| 13.2 |
|||
| |
|||
|- |
|- |
||
!rowspan=3|GeForce GT 730 |
|||
| January 26, 2016 |
|||
|rowspan=3|June 18, 2014 |
|||
| GK208-203-B1 |
|||
|23 |
|||
| PCIe 2.0 x8, PCIe x1 |
|||
|rowspan=3|$69–79 |
|||
| 192:16:8 |
|||
| 954 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 900 (1800)<br />1253 (5010) |
|||
| 7.6 |
|||
| 15.3 |
|||
| 1024<br />2048 |
|||
| 14.4<br />40.0 |
|||
| rowspan="2" | DDR3<br />GDDR5 |
|||
| 366 |
|||
| 15.3 |
|||
| rowspan="2" | 19 |
|||
| $35–45 |
|||
|- |
|- |
||
|25 |
|||
! style="text-align:left;" | GeForce GT 720<ref>{{cite web |url=http://www.techpowerup.com/gpudb/1989/geforce-gt-720.html |title=Nvidia GeForce GT 720 {{pipe}} techPowerUp GPU Database |website=Techpowerup.com |access-date=2015-12-11 |archive-url=https://archive.today/20140615091724/http://www.techpowerup.com/gpudb/1989/geforce-gt-720.html |archive-date=2014-06-15 |url-status=live }}</ref> |
|||
| March 27, 2014 |
|||
| GK208-201-B1 |
|||
| rowspan="3" | PCIe 2.0 x8 |
|||
| 192:16:8 |
|||
| 797 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 900 (1800)<br />1253 (5010) |
|||
| 6.4 |
|||
| 12.8 |
|||
| 1024<br />2048 |
|||
| 14.4<br />40.0 |
|||
| 306 |
|||
| 12.8 |
|||
| $49–59 |
|||
|- |
|- |
||
|49 |
|||
! rowspan="3" style="text-align:left;" | GeForce GT 730<br /><ref name="gt730">{{cite web |url=http://www.geforce.com/hardware/desktop-gpus/geforce-gt-730/specifications |title=GT 730 {{pipe}} Specifications |website=GeForce.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151212232644/http://www.geforce.com/hardware/desktop-gpus/geforce-gt-730/specifications |archive-date=2015-12-12 |url-status=live }}</ref>{{efn|name=geforce 700 5|The GeForce GT 730 (DDR3, 64-bit) is a rebranded GeForce GT 630 (Rev. 2).}}{{efn|name=geforce 700 6|The GeForce GT 730 (DDR3, 128-bit) is a rebranded GeForce GT 630 (128-bit).}} |
|||
| rowspan="3" | June 18, 2014 |
|||
| GK208-301-A1 |
|||
| rowspan="5" | 2 |
|||
| 384:16:8 |
|||
| 902 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 900<br />(1800) |
|||
| 7.22 |
|||
| 14.44 |
|||
| 1024<ref name="1GBgt730">{{cite web|url=https://www.zotac.com/product/graphics_card/gt-730-1gb|title=GeForce GT 730 1GB-ZOTAC|work=[[ZOTAC]]|access-date=July 12, 2017|archive-url=https://web.archive.org/web/20160719212714/https://www.zotac.com/product/graphics_card/gt-730-1gb|archive-date=July 19, 2016|url-status=live}}</ref><br />2048<br />4096 |
|||
| 14.4 |
|||
| DDR3 |
|||
| rowspan="2" | 692.7 |
|||
| rowspan="2" | 28.9 |
|||
| 23 |
|||
| rowspan="3" | $69–79 |
|||
|- |
|- |
||
!GeForce GT 740 |
|||
| GK208-400-A1 |
|||
|May 29, 2014 |
|||
| 384:16:8 |
|||
|64 |
|||
| 902 |
|||
|$89–99 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 1250<br />(5000) |
|||
| 7.22 |
|||
| 14.44 |
|||
| 1024<br />2048<ref>{{cite web |url=http://www.evga.com/products/product.aspx?pn=02G-P3-3733-KR |title=EVGA - Products - EVGA GeForce GT 730 2GB (Low Profile) - 02G-P3-3733-KR |access-date=2017-04-29 |archive-url=https://web.archive.org/web/20170215122047/http://www.evga.com/Products/Product.aspx?pn=02G-P3-3733-KR |archive-date=2017-02-15 |url-status=live }}</ref> |
|||
| 40.0 |
|||
| GDDR5 |
|||
| 25 |
|||
|- |
|- |
||
!GeForce GTX 745 |
|||
| GF108 |
|||
|rowspan=3|February 18, 2014 |
|||
| TSMC 40 nm |
|||
|rowspan=2|55 |
|||
| 585 |
|||
|OEM |
|||
| 116 |
|||
| PCIe 2.0 x16 |
|||
| 96:16:4 |
|||
| 700 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 900<br />(1800) |
|||
| 2.8 |
|||
| 11.0 |
|||
| rowspan="3" | 1024<br />2048<br />4096 |
|||
| 28.8 |
|||
| rowspan="2" | DDR3 |
|||
| 128 |
|||
| n/a |
|||
| 1.1 |
|||
| 268.8 |
|||
| 33.6 |
|||
| 49 |
|||
|- |
|- |
||
!GeForce GTX 750 |
|||
! rowspan="2" style="text-align:left;" | GeForce GT 740{{efn|name=geforce 700 7|The GeForce GT 740 (OEM) is a rebranded GeForce GTX 650.}} |
|||
|$119 |
|||
| rowspan="2" | May 29, 2014 |
|||
| rowspan="2" | GK107-425-A2 |
|||
| rowspan="14" | [[TSMC]]<br />[[28 nanometer|28HP]] |
|||
| rowspan="2" | 1270 |
|||
| rowspan="2" | 118 |
|||
| rowspan="14" | PCIe 3.0 x16 |
|||
| 384:32:16 |
|||
| 993 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 891<br />(1782) |
|||
| 15.9 |
|||
| 31.8 |
|||
| 28.5 |
|||
| rowspan="5" | 128 |
|||
| rowspan="2" | 1.2 |
|||
| rowspan="14" | 1.2 |
|||
| rowspan="2" | 762.6 |
|||
| rowspan="2" | 31.8 |
|||
| rowspan="2" | 64 |
|||
| rowspan="2" | $89–99 |
|||
|- |
|- |
||
!GeForce GTX 750 Ti |
|||
| 384:32:16 |
|||
|60 |
|||
| 993 |
|||
|$149 |
|||
| {{n/a}} |
|||
| {{n/a}} |
|||
| 1252<br />(5008) |
|||
| 15.9 |
|||
| 31.8 |
|||
| 80.1 |
|||
| GDDR5 |
|||
|- |
|- |
||
! |
!GeForce GTX 760 192-bit |
||
|October 17, 2013 |
|||
| rowspan="3" | February 18, 2014 |
|||
|130 |
|||
| GM107-220-A2 |
|||
|OEM |
|||
| rowspan="3" | 1870 |
|||
| rowspan="3" | 148 |
|||
| 3 |
|||
| 384:24:16 |
|||
| 1033 |
|||
| {{unk}} |
|||
| {{unk}} |
|||
| 900<br />(1800) |
|||
| 16.5 |
|||
| 24.8 |
|||
| 1024<br />4096 |
|||
| 28.8 |
|||
| DDR3 |
|||
| rowspan="3" | 1.3 |
|||
| 793.3 |
|||
| 24.8 |
|||
| rowspan="2" | 55 |
|||
| OEM |
|||
|- |
|- |
||
! |
!GeForce GTX 760 |
||
|June 25, 2013 |
|||
| GM107-300-A2 |
|||
|rowspan=2|170 |
|||
| 4 |
|||
|$249 ($219) |
|||
| 512:32:16 |
|||
| 1020 |
|||
| 1085 |
|||
| 1163 |
|||
| 1250<br />(5000) |
|||
| 16.3 |
|||
| 32.6 |
|||
| 1024<br />2048<br />4096<ref>{{cite web|title=AFOX GTX 750 4 GB Specs|url=https://www.techpowerup.com/gpu-specs/afox-gtx-750-4-gb.b9074|access-date=2021-08-11|website=TechPowerUp|language=en}}</ref> |
|||
| 80 |
|||
| rowspan="11" | GDDR5 |
|||
| 1044.5 |
|||
| 32.6 |
|||
| $119 |
|||
|- |
|- |
||
! |
!GeForce GTX 760 Ti |
||
|September 27, 2013 |
|||
| GM107-400-A2 |
|||
| |
|OEM |
||
| 640:40:16 |
|||
| 1020 |
|||
| 1085 |
|||
| 1200 |
|||
| 1350<br />(5400) |
|||
| 16.3 |
|||
| 40.8 |
|||
| 1024<br />2048<br />4096 |
|||
| 86.4 |
|||
| 1305.6 |
|||
| 40.8 |
|||
| 60 |
|||
| $149 |
|||
|- |
|- |
||
! |
!GeForce GTX 770 |
||
| |
|May 30, 2013 |
||
|rowspan=5|230 |
|||
| GK104-200-KD-A2 |
|||
|$399 ($329) |
|||
| rowspan="4" | 3540 |
|||
| rowspan="4" | 294 |
|||
| rowspan="2" | 6 |
|||
| 1152:96:24 |
|||
| 824 |
|||
| 888 |
|||
| 889 |
|||
| 1450<br />(5800) |
|||
| 19.8 |
|||
| 79.1 |
|||
| 1536<br />3072 |
|||
| 134.4 |
|||
| 192 |
|||
| rowspan="9" | 1.2 |
|||
| 1896.2 |
|||
| 79.0 |
|||
| 130 |
|||
| OEM |
|||
|- |
|- |
||
! |
!GeForce GTX 780 |
||
| |
|May 23, 2013 |
||
|$649 ($499) |
|||
| GK104-225-A2 |
|||
| 1152:96:32 |
|||
| 980 |
|||
| 1033 |
|||
| 1124 |
|||
| 1502<br />(6008) |
|||
| 31.4{{efn|name=geforce 700 10|As a Kepler GPC is able to rasterize 8 pixels per clock, fully enabled GK110 GPUs (780 Ti/TITAN Black) can only output 40 pixels per clock (5 GPCs), despite 48 ROPs and all SMX units being physically present. For GTX 780 and GTX 760, multiple GPC configurations with differing pixel fillrate are possible, depending on which SMXs were disabled in the chip: 5/4 GPCs, or 4/3 GPCs, respectively.}} |
|||
| 94 |
|||
| 2048<br />4096 |
|||
| 192.3 |
|||
| rowspan="3" | 256 |
|||
| 2257.9 |
|||
| 94.1 |
|||
| rowspan="2" | 170 |
|||
| $249 ($219) |
|||
|- |
|- |
||
!GeForce GTX 780 Ti |
|||
! style="text-align:left;" | GeForce GTX 760 Ti{{efn|name=geforce 700 8|The GeForce GTX 760 Ti (OEM) is a rebranded GeForce GTX 670.}} |
|||
|November 7, 2013 |
|||
| September 27, 2013<ref>{{cite web |url=https://www.techpowerup.com/gpudb/2491/geforce-gtx-760-ti-oem |title=NVIDIA GeForce GTX 760 Ti OEM Specs |access-date=2018-08-06 |archive-url=https://archive.today/20160530101755/http://www.techpowerup.com/gpudb/2491/geforce-gtx-760-ti-oem |archive-date=2016-05-30 |url-status=live }}</ref> |
|||
|$699 |
|||
| GK104 |
|||
| 7 |
|||
| 1344:112:32 |
|||
| 915 |
|||
| 980 |
|||
| 1084 |
|||
| 1502<br />(6008) |
|||
| 29.3 |
|||
| 102.5 |
|||
| 2048 |
|||
| 192.3 |
|||
| 2459.5 |
|||
| 102.5 |
|||
| OEM |
|||
|- |
|- |
||
! |
!GeForce GTX TITAN |
||
| |
|February 21, 2013 |
||
|rowspan=2|$999 |
|||
| GK104-425-A2 |
|||
| 8 |
|||
| 1536:128:32 |
|||
| 1046 |
|||
| 1085 |
|||
| 1130 |
|||
| 1752.5<br />(7010) |
|||
| 33.5 |
|||
| 134 |
|||
| 2048 4096 |
|||
| 224 |
|||
| 3213.3 |
|||
| 133.9 |
|||
| rowspan="5" | 230 |
|||
| $399 ($329) |
|||
|- |
|- |
||
! |
!GeForce GTX TITAN Black |
||
|February 18, 2014 |
|||
| May 23, 2013 |
|||
| GK110-300-A1 |
|||
| rowspan="4" | 7080 |
|||
| rowspan="4" | 561 |
|||
| 12 |
|||
| 2304:192:48 |
|||
| 863 |
|||
| 900 |
|||
| 1002 |
|||
| 1502<br />(6008) |
|||
| 41.4{{efn|name=geforce 700 10|As a Kepler GPC is able to rasterize 8 pixels per clock, fully enabled GK110 GPUs (780 Ti/TITAN Black) can only output 40 pixels per clock (5 GPCs), despite 48 ROPs and all SMX units being physically present. For GTX 780 and GTX 760, multiple GPC configurations with differing pixel fillrate are possible, depending on which SMXs were disabled in the chip: 5/4 GPCs, or 4/3 GPCs, respectively.}} |
|||
| 160.5 |
|||
| 3072 6144<ref>{{cite web |url=http://www.evga.com/articles/00830/ |title=Articles - EVGA GeForce GTX 780 6GB Step-Up Available Now! |publisher=EVGA |date=2014-03-21 |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20160113203734/http://www.evga.com/articles/00830/ |archive-date=2016-01-13 |url-status=live }}</ref> |
|||
| 288.4 |
|||
| rowspan="4" | 384 |
|||
| 3976.7 |
|||
| 165.7 |
|||
| $649 ($499) |
|||
|- |
|- |
||
!GeForce GTX TITAN Z |
|||
! style="text-align:left;" | GeForce GTX 780 Ti<ref>{{cite web |url=http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-780-ti/specifications |title=GeForce GTX780 Ti. Specifications |website=Geforce.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151212021141/http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-780-ti/specifications |archive-date=2015-12-12 |url-status=live }}</ref><ref>{{cite web |url=http://videocardz.com/47508/videocardz-nvidia-geforce-gtx-780-ti-2880-cuda-cores |title=Nvidia GeForce GTX 780 Ti has 2880 CUDA cores |website=Videocardz.com |date=31 October 2013 |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151222120538/http://videocardz.com/47508/videocardz-nvidia-geforce-gtx-780-ti-2880-cuda-cores |archive-date=2015-12-22 |url-status=live }}</ref><ref>{{cite web |url=http://web-engage.augure.com/pub/link/282593/04601926874847631383752919307-hl-com.com.html |title=PNY dévoile son nouveau foudre de guerre: la GeForce GTX 780 TI. |website=Web-engage.augure.com |access-date=2015-12-11 |url-status=dead |archive-url=https://web.archive.org/web/20131109211440/http://web-engage.augure.com/pub/link/282593/04601926874847631383752919307-hl-com.com.html |archive-date=November 9, 2013 }}</ref> |
|||
|May 28, 2014 |
|||
| November 7, 2013 |
|||
|375 |
|||
| GK110-425-B1 |
|||
|$2999 |
|||
| 15 |
|||
| 2880:240:48 |
|||
| 876 |
|||
| 928 |
|||
| 1019 |
|||
| 1752.5<br />(7010) |
|||
| 42.0{{efn|name=geforce 700 10|As a Kepler GPC is able to rasterize 8 pixels per clock, fully enabled GK110 GPUs (780 Ti/TITAN Black) can only output 40 pixels per clock (5 GPCs), despite 48 ROPs and all SMX units being physically present. For GTX 780 and GTX 760, multiple GPC configurations with differing pixel fillrate are possible, depending on which SMXs were disabled in the chip: 5/4 GPCs, or 4/3 GPCs, respectively.}} |
|||
| 210.2 |
|||
| 3072 |
|||
| 336.5 |
|||
| 5045.7 |
|||
| 210.2 |
|||
| $699 |
|||
|- |
|||
! style="text-align:left;" | GeForce GTX TITAN<ref>{{cite web |url=http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-titan |title=GeForce GTX TITAN |website=Geforce.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151205173714/http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-titan |archive-date=2015-12-05 |url-status=live }}</ref><ref>{{cite web |url=http://www.nvidia.com/titan-graphics-card |title=TITAN Graphics Card |website=Nvidia.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20130224082627/http://www.nvidia.com/titan-graphics-card |archive-date=2013-02-24 |url-status=live }}</ref><ref>{{cite web |url=http://www.anandtech.com/show/6760/nvidias-geforce-gtx-titan-part-1 |title=Nvidia's GeForce GTX Titan, Part 1: Titan For Gaming, Titan For Compute |website=Anandtech.com |access-date=2015-12-11 |archive-url=https://web.archive.org/web/20151204225432/http://www.anandtech.com/show/6760/nvidias-geforce-gtx-titan-part-1 |archive-date=2015-12-04 |url-status=live}}</ref> |
|||
| February 21, 2013 |
|||
| GK110-400-A1 |
|||
| 14 |
|||
| 2688:224:48 |
|||
| 837 |
|||
| 876 |
|||
| 993 |
|||
| 1502<br />(6008) |
|||
| 40.2 |
|||
| 187.5 |
|||
| rowspan="2" | 6144 |
|||
| 288.4 |
|||
| 4499.7 |
|||
| 1300<ref>{{cite web |url=http://www.anandtech.com/show/6774/nvidias-geforce-gtx-titan-part-2-titans-performance-unveiled/3 |title=Titan's Compute Performance (aka Ph.D Lust) - Nvidia's GeForce GTX Titan Review, Part 2: Titan's Performance Unveiled |website=Anandtech.com |access-date=2015-12-11 |quote=the calculated fp64 peak of Titan is 1.5 TFlops. However, under heavy load in fp64 mode, the card may underclock below the listed 837MHz to remain within the power and thermal specifications |archive-url=https://web.archive.org/web/20151222141607/http://www.anandtech.com/show/6774/nvidias-geforce-gtx-titan-part-2-titans-performance-unveiled/3 |archive-date=2015-12-22 |url-status=live }}</ref>-1499.9 |
|||
| rowspan="2" | $999 |
|||
|- |
|||
! style="text-align:left;" | GeForce GTX TITAN Black |
|||
| February 18, 2014 |
|||
| GK110-430-B1 |
|||
| 15 |
|||
| 2880:240:48 |
|||
| 889 |
|||
| 980 |
|||
| 1058 |
|||
| 1752.5<br />(7010) |
|||
| 42.7 |
|||
| 213.4 |
|||
| 336.5 |
|||
| 5120.6 |
|||
| 1706.9 |
|||
|- |
|||
! style="text-align:left;" | GeForce GTX TITAN Z |
|||
| May 28, 2014 |
|||
| 2x GK110-350-B1<ref>{{cite web|url=https://diy.pconline.com.cn/488/4883359_all.html|title=售价21999元!NV旗舰GTX TITAN Z评测-太平洋电脑网|date=5 June 2014|access-date=2020-08-16}}</ref> |
|||
| 2x 7080 |
|||
| 2x 561 |
|||
| 2x 15 |
|||
| 2x 2880:240:48 |
|||
| 705 |
|||
| 876 |
|||
| {{unk}} |
|||
| 1752.5<br />(7010) |
|||
| 2x 33.8 |
|||
| 2x 169 |
|||
| 2x 6144 |
|||
| 2x 336.5 |
|||
| 2x 384 |
|||
| 4.5 |
|||
| 5046x2 |
|||
| 1682x2<ref>{{cite web|url=https://www.techpowerup.com/gpu-specs/geforce-gtx-titan-z.c2575|title=NVIDIA GeForce GTX TITAN Z Specs|website=TechPowerUp|language=en|access-date=2020-02-26}}</ref> |
|||
| 375 |
|||
| $2999 |
|||
|- |
|||
! rowspan="2" | Model |
|||
! rowspan="2" | Launch |
|||
! rowspan="2" | [[Code name]] |
|||
! rowspan="2" | Fab ([[Nanometer|nm]]) |
|||
! rowspan="2" | Transistors (million) |
|||
! rowspan="2" | Die size (mm<sup>2</sup>) |
|||
! rowspan="2" | [[Computer bus|Bus]] [[I/O interface|interface]] |
|||
! rowspan="2" | SMX count |
|||
! rowspan="2" | Core config{{efn|name=geforce 700 1|[[Unified shader model|Unified shaders]]: [[texture mapping unit]]s: [[render output unit]]s}} |
|||
! colspan="4" | Clock rate |
|||
! colspan="2" | [[Fillrate]] |
|||
! colspan="4" | Memory configuration |
|||
! colspan="4" | Supported [[Application programming interface|API]] version |
|||
! colspan="2" | Processing power ([[GFLOPS]]){{efn|name=geforce 700 8|The GeForce GTX 760 Ti (OEM) is a rebranded GeForce GTX 670.}} |
|||
! rowspan="2" | [[Thermal design power|TDP]] (Watts) |
|||
! rowspan="2" | Release Price (USD) |
|||
|- |
|||
! Base ([[Hertz|MHz]]) |
|||
! Average Boost ([[Hertz|MHz]]) |
|||
! Max Boost{{efn|name=geforce 700 2|Max Boost depends on ASIC quality. For example, some GTX TITAN with over 80% ASIC quality can hit 1019 MHz by default, lower ASIC quality will be 1006 MHz or 993 MHz.}} ([[Hertz|MHz]]) |
|||
! Memory ([[Hertz|MHz]]) |
|||
! Pixel ([[Pixel|GP]]/s) |
|||
! Texture ([[Texel (graphics)|GT]]/s) |
|||
! Size ([[Megabyte|MB]]) |
|||
! Bandwidth ([[Gigabyte|GB]]/s) |
|||
! DRAM type |
|||
! Bus width ([[bit]]) |
|||
! [[Vulkan (API)|Vulkan]] |
|||
! [[Direct3D]]{{efn|name=geforce 700 3}} |
|||
! [[OpenGL]] |
|||
! [[OpenCL]] |
|||
! [[Single precision floating-point format|Single precision]] |
|||
! [[Double precision floating-point format|Double precision]] |
|||
|} |
|} |
||
{{notelist}} |
|||
===GeForce 900 series=== |
===GeForce 900 series=== |
Revision as of 17:08, 14 January 2023
Desktop GPUs
Pre-GeForce
Fahrenheit GPU List | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|
Model name | STG-2000 | Riva 128 | Riva 128ZX | Riva TNT | Vanta | Vanta LT | Riva TNT2 M64 | Riva TNT2 | Riva TNT2 Pro | Riva TNT2 Ultra |
Launch date | May 22, 1995 | August 25, 1997 | February 23, 1998 | June 15, 1998 | March 22, 1999 | March 2000 | October 1999 | March 15, 1999 | October 12, 1999 | March 15, 1999 |
GeForce 256 series
- All models are made via TSMC 220 nm fabrication process
- All models support Direct3D 7.0 and OpenGL 1.2
- All models support hardware Transform and Lighting (T&L) and Cube Environment Mapping
GeForce 256 GPU List | ||
---|---|---|
Model name | GeForce 256 SDR | GeForce 256 DDR |
Launch date | Oct 11, 1999 | Dec 13, 1999 |
GeForce2 series
- All models support Direct3D 7 and OpenGL 1.2
- All models support TwinView Dual-Display Architecture, Second Generation Transform and Lighting (T&L), Nvidia Shading Rasterizer (NSR), High-Definition Video Processor (HDVP)
- GeForce2 MX models support Digital Vibrance Control (DVC)
GeForce 2 series GPU List | ||||||||
---|---|---|---|---|---|---|---|---|
Model name | GeForce2 MX IGP + nForce 220/420 | GeForce2 MX200 | GeForce2 MX | GeForce2 MX400 | GeForce2 GTS | GeForce2 Pro | GeForce2 Ti | GeForce2 Ultra |
Launch date | June 4, 2001 | March 3, 2001 | June 28, 2000 | March 3, 2001 | April 26, 2000 | December 5, 2000 | October 1, 2001 | August 14, 2000 |
GeForce3 series
- All models are made via TSMC 150 nm fabrication process
- All models support Direct3D 8.0 and OpenGL 1.3
- All models support 3D Textures, Lightspeed Memory Architecture (LMA), nFiniteFX Engine, Shadow Buffers
GeForce3 series GPU List | |||
---|---|---|---|
Model name | GeForce3 Ti200 | GeForce3 | GeForce3 Ti500 |
Launch date | October 1, 2001 | February 27, 2001 | October 1, 2001 |
GeForce4 series
- All models are manufactured via TSMC 150 nm manufacturing process
- All models support Accuview Antialiasing (AA), Lightspeed Memory Architecture II (LMA II), nView
GeForce 4 series GPU List | ||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Model name | GeForce4 MX IGP + nForce2 | GeForce4 MX420 | GeForce4 MX440 SE | GeForce MX4000 | GeForce PCX4300 | GeForce4 MX440 | GeForce4 MX440 8x | GeForce4 MX460 | GeForce4 Ti4200 | GeForce4 Ti4200 8x | GeForce4 Ti4400 | GeForce4 Ti4400 8x (Ti4800SE) | GeForce4 Ti4600 | GeForce4 Ti4600 8x (Ti4800) |
Launch date | October 1, 2002 | February 6, 2002 | 2002 | December 14, 2003 | February 19, 2004 | February 6, 2002 | September 25, 2002 | February 6, 2002 | April 16, 2002 | September 25, 2002 | February 6, 2002 | January 20, 2003 | February 6, 2002 | January 20, 2003 |
GeForce FX (5xxx) series
- All models support Direct3D 9.0a and OpenGL 1.5 (2.1 (software) with latest drivers)
- The GeForce FX series runs vertex shaders in an array
GeForce FX (5100–5700) GPU List | ||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Model name | GeForce FX 5100 | GeForce FX 5200 LE | GeForce FX 5200 | GeForce FX 5200 Ultra | GeForce PCX 5300 | GeForce FX 5500 | GeForce FX 5600 XT | GeForce FX 5600 | GeForce FX 5600 Ultra | GeForce FX 5600 Ultra Rev.2 | GeForce FX 5700 VE | GeForce FX 5700 LE | GeForce FX 5700 | |
Launch date | March 2003 | March 6, 2003 | March 17, 2004 | March 2004 | October 2003 | March 2003 | March 6, 2003 | September 2004 | March 2004 | 2003 | ||||
GeForce FX (5750–5950) GPU List | ||||||||||||||
Model name | GeForce PCX 5750 | GeForce FX 5700 Ultra | GeForce FX 5700 Ultra GDDR3 | GeForce FX 5800 | GeForce FX 5800 Ultra | GeForce FX 5900 ZT | GeForce FX 5900 XT | GeForce FX 5900 | GeForce FX 5900 Ultra | GeForce PCX 5900 | GeForce FX 5950 Ultra | GeForce PCX 5950 | ||
Launch date | March 17, 2004 | October 23, 2003 | March 15, 2004 | January 27, 2003 | December 15, 2003 | December 15, 2003 | May 2003 | May 12, 2003 | March 17, 2004 | October 23, 2003 | February 17, 2004 |
GeForce 6 (6xxx) series
- All models support Direct3D 9.0c and OpenGL 2.1
- All models support Transparency AA (starting with version 91.47 of the ForceWare drivers) and PureVideo
GeForce 6 (6100–6600) series GPU List | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|
Model name | GeForce 6100 + nForce 410 | GeForce 6150 SE + nForce 430 | GeForce 6150 LE + nForce 430 | GeForce 6150 + nForce 430 | GeForce 6200 LE | GeForce 6200A | GeForce 6200 | GeForce 6200 TurboCache | GeForce 6500 | GeForce 6600 LE |
Launch date | October 20, 2005 | June 2006 | October 20, 2005 | 2005 | April 4, 2005 | October 12, 2004 (PCIe) | December 15, 2004 | October 1, 2005 | 2005 | |
January 17, 2005 (AGP) | ||||||||||
GeForce 6 (6600–6800) series GPU List | ||||||||||
Model name | GeForce 6600 | GeForce 6600 GT | GeForce 6800 LE | GeForce 6800 XT | GeForce 6800 | GeForce 6800 GTO | GeForce 6800 GS | GeForce 6800 GT | GeForce 6800 Ultra | GeForce 6800 Ultra Extreme Edition |
Launch date | August 12, 2004 | August 12, 2004 (PCIe) | January 16, 2005 (PCIe) | September 30, 2005 | November 8, 2004 (PCIe) | April 14, 2004 | November 7, 2005 (PCIe) | June 28, 2004 (PCIe) | June 28, 2004 (PCIe) | May 4, 2004 |
November 14, 2004 (AGP) | July 22, 2004 (AGP) | April 14, 2004 (AGP) | December 8, 2005 (AGP) | May 4, 2004 (AGP) | May 4, 2004 (AGP) | |||||
March 14, 2005 (512 MB) |
GeForce 7 (7xxx) series
- All models support Direct3D 9.0c and OpenGL 2.1
- All models support Transparency AA (starting with version 91.47 of the ForceWare drivers)
GeForce 7 (7025 – 7300 LE) GPU List | |||||||||
---|---|---|---|---|---|---|---|---|---|
Model name | GeForce 7025 + nForce 630a | GeForce 7050PV + nForce 630a | GeForce 7050 + nForce 610i/630i | GeForce 7100 + nForce 630i | GeForce 7150 + nForce 630i | GeForce 7100 GS | GeForce 7200 GS | GeForce 7300 SE | GeForce 7300 LE |
Launch date | July 2007 | August 8, 2006 | January 18, 2006 | March 22, 2006 | |||||
GeForce 7 (7300 GS–8700 GT) GPU List | |||||||||
Model name | GeForce 7300 GS | GeForce 7300 GT | GeForce 7500 LE | GeForce 7600 GS | GeForce 7600 GT | GeForce 7600 GT 80 nm | GeForce 7650 GS | GeForce 7800 GS | GeForce 7800 GT |
Launch date | January 18, 2006 | May 15, 2006 | 2006 | March 22, 2006 (PCIe)
July 1, 2006 (AGP) |
March 9, 2006 (PCIe)
July 15, 2006 (AGP) |
January 8, 2007 | March 22, 2006 | February 2, 2006 | August 11, 2005 |
GeForce 7 (7800 GTX–7950 GX2) GPU List | |||||||||
Model name | GeForce 7800 GTX | GeForce 7900 GS | GeForce 7900 GT | GeForce 7900 GTO | GeForce 7900 GTX | GeForce 7900 GX2 | GeForce 7950 GT | GeForce 7950 GX2 | |
Launch date | June 22, 2005 (256 MB)
November 14, 2005 (512 MB) |
May 2006 (PCIe)
April 2, 2007 (AGP) |
March 9, 2006 | October 1, 2006 | March 9, 2006 | September 6, 2006 (PCIe)
April 2, 2007 (AGP) |
June 5, 2006 |
GeForce 8 (8xxx) series
- All models support coverage sample anti-aliasing, angle-independent anisotropic filtering, and 128-bit OpenEXR HDR.
GeForce 8 (8100–1600 GS) GPU List | |||||||||
---|---|---|---|---|---|---|---|---|---|
Model name | GeForce 8100 mGPU | GeForce 8200 mGPU | GeForce 8300 mGPU | GeForce 8300 GS | GeForce 8400 GS | GeForce 8400 GS rev.2 | GeForce 8400 GS rev.3 | GeForce 8500 GT | GeForce 8600 GS |
Launch date | 2008 | July 2007 | June 15, 2007 | December 10, 2007 | July 12, 2010 | April 17, 2007 | April 2007 | ||
GeForce 8 (8600 GT–8800) GPU List | |||||||||
Model name | GeForce 8600 GT | GeForce 8600 GTS | GeForce 8800 GS | GeForce 8800 GTS (G80) | GeForce 8800 GTS 112 (G80) | GeForce 8800 GT | GeForce 8800 GTS (G92) | GeForce 8800 GTX | GeForce 8800 Ultra |
Launch date | April 17, 2007 | January 2008 | February 12, 2007 (320)
November 8, 2006 (640) |
November 19, 2007 | October 29, 2007 (512)
December 11, 2007 (256, 1024) |
December 11, 2007 | November 8, 2006 | May 2, 2007 |
GeForce 9 (9xxx) series
- All models support Coverage Sample Anti-Aliasing, Angle-Independent Anisotropic Filtering, 128-bit OpenEXR HDR
GeForce 9 (9300–9600 GSO) GPU List | ||||||||
---|---|---|---|---|---|---|---|---|
Model name | GeForce 9300 mGPU | GeForce 9400 mGPU | GeForce 9300 GE | GeForce 9300 GS | GeForce 9400 GT | GeForce 9500 GT | GeForce 9600 GS | GeForce 9600 GSO |
Launch date | October 2008 | June 2008 | August 27, 2008 | July 29, 2008 | May 2008 | |||
GeForce 9 (9600 GSO 512–9800) GPU List | ||||||||
Model name | GeForce 9600 GSO 512 | GeForce 9600 GT Green Edition | GeForce 9600 GT | GeForce 9800 GT Green Edition | GeForce 9800 GT | GeForce 9800 GTX | GeForce 9800 GTX+ | GeForce 9800 GX2 |
Launch date | October 2008 | 2009 | February 21, 2008 | 2009 | July 2008 | April 1, 2008 | July 16, 2008 | March 18, 2008 |
GeForce 100 series
GeForce 100 series GPU List | |||||
---|---|---|---|---|---|
Model name | GeForce G 100 | GeForce GT 120 | GeForce GT 130 | GeForce GT 140 | GeForce GTS 150 |
Launch date | March 10, 2009 |
GeForce 200 series
- All models support Coverage Sample Anti-Aliasing, Angle-Independent Anisotropic Filtering, 240-bit OpenEXR HDR
Model name | Launch date | Release Price (USD) |
---|---|---|
GeForce 205 | November 26, 2009 | |
GeForce 210 | October 12, 2009 | |
GeForce GT 220 | ||
GeForce GT 230 | October 12, 2009 | |
April 27, 2009 | ||
GeForce GT 240 | November 17, 2009 | |
GeForce GTS 240 | July 1, 2009 | |
GeForce GTS 250 | 2009 | |
March 3, 2009 | ||
GeForce GTX 260 | June 16, 2008 | |
September 16, 2008
November 27, 2008 (55 nm) | ||
GeForce GTX 275 | April 9, 2009 | |
GeForce GTX 280 | June 17, 2008 | |
GeForce GTX 285 | January 15, 2009 | |
GeForce GTX 295 | January 8, 2009 |
GeForce 300 series
Model name | Launch date |
---|---|
GeForce 310 | November 27, 2009 |
GeForce 315 | February 2010 |
GeForce GT 320 | |
GeForce GT 330 | |
GeForce GT 340 |
GeForce 400 series
- All cards have a PCIe 2.0 x16 Bus interface.
- The base requirement for Vulkan 1.0 in terms of hardware features was OpenGL ES 3.1 which is a subset of OpenGL 4.3, which is supported on all Fermi and newer cards.
- Memory bandwidths stated in the following table refer to Nvidia reference designs. Actual bandwidth can be higher or lower depending on the maker of the graphic board.
Model name | Launch date | TDP (Watts) | Release Price (USD) |
---|---|---|---|
GeForce 405 | September 16, 2011 | 30.5 | OEM |
GeForce GT 420 | September 3, 2010 | 50 | |
GeForce GT 430 | October 11, 2010 | 60 | |
49 | $79 | ||
GeForce GT 440 | October 11, 2010 | 56 | OEM |
February 1, 2011 | 65 | $100 | |
GeForce GTS 450 | October 11, 2010 | 106 | OEM |
September 13, 2010 March 15, 2011 |
$129 | ||
GeForce GTX 460 SE | November 15, 2010 | 150 | $160 |
GeForce GTX 460 | October 11, 2010 | 150 | OEM |
July 12, 2010 | $199 | ||
160 | $229 | ||
September 24, 2011 | $199 | ||
GeForce GTX 465 | May 31, 2010 | 200 | $279 |
GeForce GTX 470 | March 26, 2010 | 215 | $349 |
GeForce GTX 480 | March 26, 2010 | 250 | $499 |
GeForce 500 series
Model name | Launch date | TDP (Watts) | Release Price (USD) |
---|---|---|---|
GeForce 510 | September 29, 2011 | 25 | OEM |
GeForce GT 520 | April 12, 2011 | 29 | $59 |
GeForce GT 530 | May 14, 2011 | 50 | OEM |
GeForce GT 545 | 105 | ||
70 | $149 | ||
GeForce GTX 550 Ti | March 15, 2011 | 116 | $149 |
GeForce GTX 555 | May 14, 2011 | 150 | OEM |
GeForce GTX 560 SE | February 20, 2012 | ||
GeForce GTX 560 | May 17, 2011 | $199 | |
GeForce GTX 560 Ti | May 30, 2011 | 210 | OEM |
January 25, 2011 | 170 | $249 | |
GeForce GTX 560 Ti 448 Cores | November 29, 2011 | 210 | $289 |
GeForce GTX 570 | December 7, 2010 | 219 | $349 |
GeForce GTX 580 | November 9, 2010 | 244 | $499 |
GeForce GTX 590 | March 24, 2011 | 365 | $699 |
GeForce 600 series
- Add NVENC on GTX cards
- Several 600 series cards are rebranded 400 or 500 series cards.
Model name | Launch date | TDP (Watts) | Release Price (USD) |
---|---|---|---|
GeForce 605 | April 3, 2012 | 25 | OEM |
GeForce GT 610 | May 15, 2012 | 29 | Retail |
GeForce GT 620 | April 3, 2012 | 30 | OEM |
May 15, 2012 | 49 | Retail | |
GeForce GT 625 | February 19, 2013 | 30 | OEM |
GeForce GT 630 | April 24, 2012 | 50 | |
May 15, 2012 | 49 | Retail | |
65 | |||
May 29, 2013 | 25 | ||
GeForce GT 635 | February 19, 2013 | 35 | OEM |
GeForce GT 640 | April 24, 2012 | 50 | |
75 | |||
June 5, 2012 | 65 | $100 | |
April 24, 2012 | 75 | OEM | |
May 29, 2013 | 49 | ||
GeForce GT 645 | April 24, 2012 | 140 | OEM |
GeForce GTX 645 | April 22, 2013 | 64 | |
GeForce GTX 650 | September 13, 2012 | $110 | |
November 27, 2013 | ? | ||
GeForce GTX 650 Ti | October 9, 2012 | 110 | $150 (130) |
GeForce GTX 650 Ti Boost | March 26, 2013 | 134 | $170 (150) |
GeForce GTX 660 | August 22, 2012 | 130 | OEM |
September 13, 2012 | 140 | $230 (180) | |
GeForce GTX 660 Ti | August 16, 2012 | 150 | $300 |
GeForce GTX 670 | May 10, 2012 | 170 | $400 |
GeForce GTX 680 | March 22, 2012 | 195 | $500 |
GeForce GTX 690 | April 29, 2012 | 300 | $1000 |
GeForce 700 series
The GeForce 700 series for desktop. The GM107-chips are Maxwell-based, the GKxxx-chips Kepler.
- Improve NVENC
Model name | Launch date | TDP (Watts) | Release Price (USD) |
---|---|---|---|
GeForce GT 705 | March 27, 2014 | 29 | OEM |
GeForce GT 710 | OEM | ||
January 26, 2016 | 19 | $35–45 | |
GeForce GT 720 | March 27, 2014 | $49–59 | |
GeForce GT 730 | June 18, 2014 | 23 | $69–79 |
25 | |||
49 | |||
GeForce GT 740 | May 29, 2014 | 64 | $89–99 |
GeForce GTX 745 | February 18, 2014 | 55 | OEM |
GeForce GTX 750 | $119 | ||
GeForce GTX 750 Ti | 60 | $149 | |
GeForce GTX 760 192-bit | October 17, 2013 | 130 | OEM |
GeForce GTX 760 | June 25, 2013 | 170 | $249 ($219) |
GeForce GTX 760 Ti | September 27, 2013 | OEM | |
GeForce GTX 770 | May 30, 2013 | 230 | $399 ($329) |
GeForce GTX 780 | May 23, 2013 | $649 ($499) | |
GeForce GTX 780 Ti | November 7, 2013 | $699 | |
GeForce GTX TITAN | February 21, 2013 | $999 | |
GeForce GTX TITAN Black | February 18, 2014 | ||
GeForce GTX TITAN Z | May 28, 2014 | 375 | $2999 |
GeForce 900 series
- All models support the following APIs: Direct3D 12_1, OpenGL 4.6, OpenCL 3.0 and Vulkan 1.3[1] and CUDA 5.2
- Improve NVENC (YUV4:4:4, predictive lossless encoding).
- Add H265 hardware support on GM20x
- GM108 does not have NVENC hardware encoder support.
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus interface | L2 Cache (MB) |
Clock Speeds | Memory | Fillrate[b] | Processing power (GFLOPS)[b][c] | TDP (Watts) | SLI support | Release price (USD) | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base (MHz) | Boost (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[d] | Texture (GT/s)[e] | Single precision | Double precision | MSRP | |||||||||||
GeForce GT 945A[2][3][4] | February, 2016 | GM108 | TSMC 28HP |
Unknown | Unknown | 512:24:8 (4) | PCIe 3.0 x8 | ? | 1072 | 1176 | 1800 | 1 / 2 | 14.4 | DDR3 / GDDR5 | 64 | 8.5 9.4 |
25.7 28.2 |
1,097.7 1,204.2 |
34.3 37.6 |
33 | No | OEM |
GeForce GTX 950[5] | August 20, 2015 | GM206-250 | 2.94 | 227 | 768:48:32 (6) | PCIe 3.0 x16 | 1 | 1024 | 1188 | 6600 | 2 | 105.7 | GDDR5 | 128 | 32.7 38.0 |
49.1 57.0 |
1,572.8 1,824.7 |
49.1 57.0 |
90 (75[f]) | 2-way SLI | $159 | |
GeForce GTX 950 (OEM)[7] | Unknown | GM206 | 1024:64:32 (8) | 935 | Unknown | 5000 | 80.0 | 29.9 |
59.8 |
1,914.9 , |
59.8 |
Unknown | OEM | |||||||||
GeForce GTX 960[8] | January 22, 2015 | GM206-300 | 1127 | 1178 | 7000 | 2 4[g] |
112.1 | 36.0 37.6 |
72.1 75.3 |
2,308.0 2,412.5 |
72.1 75.3 |
120 | $199 | |||||||||
GeForce GTX 960 (OEM)[10] | Unknown | GM204 | 5.2 | 398 | 1280:80:48 (10) | 924 | Unknown | 5000 | 3 | 120.0 | 192 | 44.3 |
73.9 |
2,365.4 , |
73.9 |
Unknown | OEM | |||||
GeForce GTX 970[11] | September 18, 2014 | GM204-200 | 1664:104:56 (13) | 1.75 | 1050 | 1178 | 7000 | 3.5 + 0.5[h] |
196.3 + 28.0[h] |
224 + 32[h] |
58.8 65.9 |
109.2 122.5 |
3,494.4 3,920.3 |
109.2 122.5 |
145 | 4-way SLI | $329 | |||||
GeForce GTX 980[13] | September 18, 2014 | GM204-400 | 2048:128:64 (16) | 2 | 1126 | 1216 | 4 | 224.3 | 256 | 72.0 77.8 |
144.1 155.6 |
4,612.0 4,980.7 |
144.1 155.6 |
165 | $549 | |||||||
GeForce GTX 980 Ti[14] | June 1, 2015 | GM200-310 | 8 | 601 | 2816:176:96 (22) | 3 | 1000 | 1075 | 6 | 336.5 | 384 | 96.0 103.2 |
176.0 189.2 |
5,632.0 6,054.4 |
176.0 189.2 |
250 | $649 | |||||
GeForce GTX TITAN X[15] | March 17, 2015 | GM200-400 | 3072:192:96 (24) | 12 | 192.0 206.4 |
6,144.0 6,604.8 |
192.0 206.4 |
$999 |
- ^ Main shader processors : texture mapping units : render output units (streaming multiprocessors)
- ^ a b Base clock, Boost clock
- ^ To calculate the processing power see Maxwell (microarchitecture)#Performance.
- ^ Pixel fillrate is calculated as the number of ROPs multiplied by the respective core clock speed.
- ^ Texture fillrate is calculated as the number of TMUs multiplied by the respective core clock speed.
- ^ Some GTX950 cards were released without power connector powered only by PCIe slot. These had limited power consumption and TPD to 75W.[6]
- ^ Some manufacturers produced 4 GB versions of GTX 960. These were often criticized as useless move, as titles that would use so much VRAM and actually gain advantage over 2 GB versions, would already run too slow on those resolutions and settings, as GTX960 didn't have enough compute power and memory bandwidth to handle it.[9]
- ^ a b c For accessing its memory, the GTX 970 stripes data across 7 of its 8 32-bit physical memory lanes, at 196 GB/s. The last 1/8 of its memory (0.5 GB on a 4 GB card) is accessed on a non-interleaved solitary 32-bit connection at 28 GB/s, one seventh the speed of the rest of the memory space. Because this smaller memory pool uses the same connection as the 7th lane to the larger main pool, it contends with accesses to the larger block reducing the effective memory bandwidth not adding to it as an independent connection could.[12]
GeForce 10 series
- Supported display standards: DP 1.4 (no DSC), HDMI 2.0b, Dual-link DVI[a][16]
- Supported APIs: Direct3D 12 (12_1), OpenGL 4.6, OpenCL 3.0, Vulkan 1.3[1] and CUDA 6.1
- Improved NVENC (HEVC Main10, decode 8K30, etc.)
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[b] | Bus interface | L2 Cache (MB) |
Clock speeds | Memory | Fillrate[c] | Processing power (GFLOPS)[c][d] | TDP (Watts) | SLI support | Release price (USD) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[e][f] | Texture (GT/s)[g] | Single precision | Double precision | Half precision | MSRP | Founders Edition | |||||||||||
GeForce GT 1010[19] | January 13, 2021 | GP108 | Samsung 14LPP |
1.8 | 74 | 256:16:16 | PCIe 3.0 x4 | 0.25 | 1228 | 1468 | 5000 | 2 | 40.1 | GDDR5 | 64 | 23.5 | 23.5 | 751.6 | 23.5 | ? | 30 | No | Unknown | — |
GeForce GT 1030[20][21] | March 12, 2018 | GP108-310-A1 | 384:24:16 (3) (1) |
PCIe 3.0 x4[22][23] | ? | 1152 | 1379 | 2100 | 16.8 | DDR4 | 18.4 22.0 |
27.6 33.0 |
884.7 1,059.0 |
27.6 33.0 |
13.8 16.5 |
20 | $79 | |||||||
May 17, 2017 | GP108-300-A1 | 0.5 | 1227 | 1468 | 6000 | 48.0 | GDDR5 | 19.6 23.4 |
29.4 35.2 |
942.3 1,127.4 |
29.4 35.2 |
14.7 17.6 |
30 | $70 | ||||||||||
GeForce GTX 1050[24] | October 25, 2016 | GP107-300-A1 | 3.3 | 132 | 640:40:32 (5) (2) |
PCIe 3.0 x16 | 1 | 1354 | 1455 | 7000 | 112.0 | 128 | 43.3 46.6 |
54.1 58.8 |
1,733.1 1,862.4 |
54.1 58.2 |
27.0 29.1 |
75 (Retail up to 120) |
$109 | |||||
May 21, 2018 | GP107-301-A1 | 768:48:24 (6) (2) |
0.75 | 1392 | 1518 | 3 | 84.0 | 96 | 33.4 36.4 |
66.8 72.9 |
2,138.1 2,331.6 |
66.8 72.9 |
33.4 36.4 |
Unknown | ||||||||||
GeForce GTX 1050 Ti[24] | October 25, 2016 | GP107-400-A1 | 768:48:32 (6) (2) |
1 | 1290 | 1392 | 4 | 112.0 | 128 | 41.2 44.5 |
61.9 66.8 |
1,981.4 2,138.1 |
61.9 66.8 |
30.9 33.4 |
$139 | |||||||||
GeForce GTX 1060 [25][26][27][28] |
December 25, 2016 | GP104-140-A1 | TSMC 16FF |
7.2 | 314 | 1152:72:48 (9) (2) |
1.5? | 1506 | 1708 | 8000 | 3 | 192.0 | 192 | 72.2 81.9 |
108.4 122.9 |
3,469.8 3,935.2 |
108.4 122.9 |
54.2 61.4 |
120 (Retail up to 200) |
$199 | ||||
August 18, 2016 | GP106-300-A1 | 4.4 | 200 | 1.5 | ||||||||||||||||||||
December 26, 2017 | GP106-350-K3-A1 | 1280:80:48 (10) (2) |
1.25 | 5 | 160.0 | 160 | 60.2 68.3 |
120.4 136.7 |
3,855.3 4,375.0 |
120.4 136.7 |
60.2 68.3 |
OEM | ||||||||||||
March 8, 2018 | GP104-150-A1 | 7.2 | 314 | 1280:80:48 (10) (2) |
1.5 | 6 | 192.0 | 192 | 72.2 82.0 |
Unknown | ||||||||||||||
December, 2018 | GP104-150-KA-A1 | GDDR5X | ||||||||||||||||||||||
July 19, 2016 | GP106-400-A1 | 4.4 | 200 | 1.5? | GDDR5 | $249 | $299 | |||||||||||||||||
April 20, 2017 | GP106-410-A1 | 9000 | 216.0 | $299 | — | |||||||||||||||||||
GeForce GTX 1070[29][30] | June 10, 2016 / Dec. 2018 |
GP104-200-A1 | 7.2 | 314 | 1920:120:64 (15) (3) |
2 | 1683 | 8000 | 8 | 256.0 | GDDR5 GDDR5X |
256 | 96.3 107.7 |
180.7 201.9 |
5,783.0 6,462.7 |
180.7 201.9 |
90.3 100.9 |
150 (Retail up to 250) |
4-way SLI or 2-way SLI HB[31][32] | $379 | $449 ($399)[33] | |||
GeForce GTX 1070 Ti[29] | November 2, 2017 | GP104-300-A1 | 2432:152:64 (19) (4) |
1607 | GDDR5 | 102.8 107.7 |
244 256 |
7,816.4 8,186.1 |
244.2 255.8 |
122.1 127.9 |
180 (Retail up to 300) |
$449 | ||||||||||||
GeForce GTX 1080[34] | May 27, 2016 | GP104-400-A1 | 2560:160:64 (20) (4) |
1733 | 10000 | 320.0 | GDDR5X | 102.8 110.9 |
257.1 277.2 |
8,227.8 8,872.9 |
257.1 277.2 |
128.5 138.6 |
$599 ($499)[33] | $699 ($549)[33] | ||||||||||
April 20, 2017 | GP104-410-A1 | 11000 | 352.0 | |||||||||||||||||||||
GeForce GTX 1080 Ti[35] | March 5, 2017 | GP102-350-K1-A1 | 12 | 471 | 3584:224:88 (28) (6) |
2.75 | 1480 | 1582 | 11 | 484.0 | 352 | 130.2 139.2 |
331.5 354.3 |
10,608.6 11,339.7 |
331.5 354.3 |
165.7 177.1 |
250 | $699 | ||||||
Nvidia TITAN X[36] | August 2, 2016 | GP102-400-A1 | 3584:224:96 (28) (6) |
3 | 1417 | 1531 | 10000 | 12 | 480.0 | 384 | 136.0 146.9 |
317.4 342.9 |
10,157.0 10,974.2 |
317.4 342.9 |
158.7 171.4 |
$1200 | — | |||||||
Nvidia TITAN Xp[37] | April 6, 2017 | GP102-450-A1 | 3840:240:96 (30) (6) |
1405 | 1480 | 11400 | 547.7 | 134.8 142.0 |
337.2 355.2 |
10,790.4 11,366.4 |
337.2 355.2 |
168.6 177.6 | ||||||||||||
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[b] | Bus interface | L2 Cache (MB) |
Base core clock (MHz) | Boost core clock (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[e][h] | Texture (GT/s)[g] | Single precision | Double precision | Half precision | TDP (Watts) | SLI support | MSRP | Founders Edition |
Clock speeds | Memory | Fillrate[c] | Processing power (GFLOPS)[c][d] | Release price (USD) |
- ^ The NVIDIA TITAN Xp and the Founders Edition GTX 1080 Ti do not have a dual-link DVI port, but a DisplayPort to single-link DVI adapter is included in the box.
- ^ a b Main shader processors : texture mapping units : render output units (streaming multiprocessors) (graphics processing clusters)
- ^ a b c d Base clock, Boost clock
- ^ a b To calculate the processing power see Pascal (microarchitecture)#Performance.
- ^ a b Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
- ^ As the GTX 1070 has one of the four GP104 GPCs disabled in the die, its frontend is only able to rasterize 48 pixels per clock.[17] Analogically, the GTX 1060 features only two GPCs on its GP106 die, meaning that its frontend can only rasterize 32 pixels per clock. The remaining backend ROPs can still be used for tasks such as MSAA.[18]
- ^ a b Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
- ^ As the GTX 1070 has one of the four GP104 GPCs disabled in the die, its frontend is only able to rasterize 48 pixels per clock.[17] Analogically, the GTX 1060 features only two GPCs on its GP106 die, meaning that its frontend can only rasterize 32 pixels per clock. The remaining backend ROPs can still be used for tasks such as MSAA.[18]
Volta series
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus Interface | L2 Cache (MB) |
Clock speeds | Memory | Fillrate[b] | Processing power (GFLOPS)[b] | TDP (Watts) | NVLink Support | Release price (USD) | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[c] | Texture (GT/s)[d] | Single precision | Double precision | Half precision | Tensor compute + Single precision | MSRP | Founders Edition | |||||||||||
Nvidia TITAN V[38] | December 7, 2017 | GV100-400-A1 | TSMC 12FFN |
21.1 | 815 | 5120:320:96:640 (80) (6) |
PCIe 3.0 x16 | 4.5 | 1200 | 1455 | 1700 | 12 | 652.8 | HBM2 | 3072 | 153.6 186.2 |
384.0 465.6 |
12,288.0 14,899.2 |
6,144.0 7,449.6 |
24,576.0 29,798.4 |
110,592.0 134,092.8 |
250 | No | $2999 | — |
Nvidia TITAN V CEO Edition[39][40] |
June 21, 2018 | GV-100-???-A1 | 5120:320:128:640 (80) (6) |
6 | 32 | 870.4 | 4096 | No | — |
- ^ Main shader processors : texture mapping units : render output units : tensor cores (streaming multiprocessors) (graphics processing clusters)
- ^ a b Base clock, Boost clock
- ^ Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
- ^ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
GeForce 16 series
- Supported APIs: Direct3D 12 (feature level 12_1), OpenGL 4.6, OpenCL 3.0, Vulkan 1.3[1] and CUDA 7.5
- NVENC 6th generation (B-frame, etc.)
- TU117 only supports Volta NVENC (5th generation)
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus interface | L2 Cache (MB) | Clock speeds | Memory | Fillrate[b] | Processing power (GFLOPS)[b] | TDP (Watts) | NVLink support | Release price (USD) | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (GT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[c] | Texture (GT/s)[d] | Single precision | Double precision | Half precision | ||||||||||||
GeForce GTX 1630 | June 28, 2022[41] | TU117-150-A1 | TSMC 12FFN |
4.7 | 200 | 512:32:16:1024:0 (8) (?) |
PCIe 3.0 x16 | 1 | 1740 | 1785 | 12 | 4 | 96 | GDDR6 | 64 | 28.56 | 57.12 | 1,781.76 1,827.84 |
55.68 57.12 |
3,563.52 3,655.68 |
75 | No | ? |
GeForce GTX 1650[42] | April 23, 2019 | TU117-300-A1 | 896:56:32:1792:0 (14) (2) |
1485 | 1665 | 8 | 128 | GDDR5 | 128 | 47.52 | 83.16 | 2,661.00 2,984.00 |
83.16 93.24 |
5,322.00 5,967.00 |
$149 | ||||||||
April 3, 2020[43] | 1410 | 1590 | 12 | 192 | GDDR6 | 45.12 | 78.96 | 2,526.72 2,849.28 |
78.96 89.04 |
5,053.44 5,698.56 | |||||||||||||
June 18, 2020[44] | TU106-125-A1 | 10.8 | 445 | 50.88 | 89.04 | 90 | |||||||||||||||||
GeForce GTX 1650 Super[45] | November 22, 2019[46] | TU116-250-KA-A1[47] | 6.6 | 284 | 1280:80:32:2560:0 (20) (3) |
1.5 | 1530 | 1725 | 48.96 | 122.40 | 3,916.80 4,416.00 |
122.40 138.00 |
7,833.60 8,832.00 |
100 | $159 | ||||||||
GeForce GTX 1660[48] | March 14, 2019 | TU116-300-A1 | 1408:88:48:2816:0 (22) (3) |
1785 | 8 | 6 | GDDR5 | 192 | 73.44 | 134.64 | 4,308.00 5,027.00 |
134.64 157.08 |
8,616.00 10,053.00 |
120 | $219 | ||||||||
GeForce GTX 1660 Super[49] | October 29, 2019 | TU116-300-A1 | 14 | 336 | GDDR6 | 125 | $229 | ||||||||||||||||
GeForce GTX 1660 Ti[50] | February 21, 2019 | TU116-400-A1 | 1536:96:48:3072:0 (24) (3) |
1500 | 1770 | 12 | 288 | 72.00 | 144.00 | 4,608.00 5,437.44 |
144.00 169.92 |
9,216.00 10,874.88 |
120 | $279 |
GeForce 20 series
- Supported APIs: Direct3D 12 Ultimate (12_2), OpenGL 4.6, OpenCL 3.0, Vulkan 1.3[1] and CUDA 7.5
- Unlike previous generations the RTX Non-Super (RTX 2070, RTX 2080, RTX 2080 Ti) Founders Edition cards no longer have reference clocks, but are "Factory-OC". However, RTX Supers (RTX 2060 Super, RTX 2070 Super, and RTX 2080 Super) Founders Edition are reference clocks.
- NVENC 6th generation (B-frame, etc.)
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus interface | L2 Cache (MB) |
Clock speeds | Memory | Fillrate[b] | Processing power (GFLOPS)[b] | Ray-tracing Performance | TDP (Watts) | NVLink support | Release price (USD) | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (GT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s)[c] | Texture (GT/s)[d] | Single precision | Double precision | Half precision | Tensor compute (FP16) | Rays/s (Billions) | RTX OPS/s (Trillions) | MSRP | Founders Edition | |||||||||||
GeForce RTX 2060[51] | January 15, 2019 | TU106-200-KA-A1 | TSMC 12FFN |
10.8 | 445 | 1920:120:48:240:30 (30) (3) |
PCIe 3.0 x16 | 3 | 1365 | 1680 | 14 | 6 | 336.0 | GDDR6 | 192 | 65.52 80.64 |
163.80 201.60 |
5 241.60 6,451.20 |
163.80 201.60 |
10 483.20 12 902.40 |
41 932.80 51 609.60 |
5 | 37 | 160 | No | $349 | — |
January 10, 2020 | TU104-150-KC-A1[52] | 13.6 | 545 | $299 | |||||||||||||||||||||||
December 7, 2021[53] | TU106-300-KA-A1 | 10.8 | 445 | 2176:136:64:272:34 (34) (3) |
1470 | 1650 | 12 | 79.20 |
199.92 224.40 |
6 400.00 7 180.00 |
199.92 224.40 |
12 800.00 14 360.00 |
185 | ||||||||||||||
GeForce RTX 2060 Super[54][55] | July 9, 2019 | TU106-410-A1 | 4 | 8 | 448.0 | 256 | 94.08 105.60 |
51,200.00 57,440.00 |
6 | 41 | 175 | $399 | |||||||||||||||
GeForce RTX 2070[56][57] | October 17, 2018 | TU106-400-A1 | 2304:144:64:288:36 (36) (3) |
1410 | 1620 | 90.24 103.68 |
203.04 233.28 |
6,497.28 7,464.96 |
203.04 233.28 |
12,994.56 14,929.92 |
51,978.24 59,719.68 |
42 | $499 | $599 | |||||||||||||
GeForce RTX 2070 Super[54][58] | July 9, 2019 | TU104-410-A1 | 13.6 | 545 | 2560:160:64:320:40 (40) (5) |
1605 | 1770 | 102.70 113.28 |
256.80 283.20 |
8,220.00 9,060.00 |
256.80 283.20 |
16,440.00 18,120.00 |
65,760.00 72,480.00 |
7 | 52 | 215 | 2-way NVLink | $499 | |||||||||
GeForce RTX 2080[59][60] | September 20, 2018 | TU104-400-A1 | 2944:184:64:368:46 (46) (6) |
1515 | 1710 | 96.96 109.44 |
278.76 314.64 |
8,920.32 10,068.48 |
278.76 314.64 |
17,840.64 20,136.96 |
71,362.56 80,547.84 |
8 | 57 | $699 | $799 | ||||||||||||
GeForce RTX 2080 Super[54][61] | July 23, 2019 | TU104-450-A1 | 3072:192:64:384:48 (48) (6) |
1650 | 1815 | 15.5 | 496.0 | 105.60 116.16 |
316.80 348.48 |
10,140.00 11,150.00 |
316.80 348.50 |
20,280.00 22,300.00 |
81,120.00 89,200.00 |
63 | 250 | $699 | |||||||||||
GeForce RTX 2080 Ti[62] | September 27, 2018 | TU102-300-K1-A1 | 18.6 | 754 | 4352:272:88:544:68 (68) (6) |
5.5 | 1350 | 1545 | 14 | 11 | 616.0 | 352 | 118.80 135.96 |
367.20 420.24 |
11,750.40 13,447.68 |
367.20 420.24 |
23,500.80 26,895.36 |
94,003.20 107,581.44 |
10 | 76 | $999 | $1,199 | |||||
Nvidia TITAN RTX[63] | December 18, 2018 | TU102-400-A1 | 4608:288:96:576:72 (72) (6) |
6 | 1770[e] | 24 | 672.0 | 384 | 129.60 169.92 |
388.80 509.76 |
12 441.60 16 312.32 |
388.80 509.76 |
24 883.20 32 624.64 |
99 532.80 130 498.56 |
11 | 84 | 280 | — | $2,499 |
- ^ a b Main shader processors : texture mapping units : render output units : tensor cores (or FP16 cores in GeForce 16 series) : ray-tracing cores (streaming multiprocessors) (graphics processing clusters)
- ^ a b c d Base clock, Boost clock
- ^ a b Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
- ^ a b Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
- ^ Boost of the Founders Editions, as there is no reference version of this card.
GeForce 30 series
- Supported APIs: Direct3D 12 Ultimate (12_2), OpenGL 4.6, OpenCL 3.0, Vulkan 1.3[1] and CUDA 8.6
- Supported display connections: HDMI 2.1, DisplayPort 1.4a
- NVENC 7th generation
- Tensor core 3rd gen
- RT core 2nd gen
- RTX IO
- Improved NVDEC with AV1 decode
- NVIDIA DLSS 2.0
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus interface | L2 Cache (MB) |
Clock speeds | Memory | Fillrate | Processing power (TFLOPS) | Ray-tracing Performance | TDP (Watts) | NVLink support | Release price (USD) | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s) | Texture (GT/s) | Single precision | Double precision | Half precision | Tensor compute (FP16) (2:1 sparse) | Rays/s (Billions) | RTX OPS/s (Trillions) | Ray Perf TFLOPS | MSRP | Founders Edition | |||||||||||
GeForce RTX 3050[64] | December 16, 2022 | GA107-150-A1 | Samsung 8LPP |
2560:80:32:80:20 | PCIe 4.0 x8 | 1552 | 1777 | 14000 | 8 | 224.0 | GDDR6 | 128 | 115 | $249 | ||||||||||||||
January 27, 2022[65] | GA106-150-A1 | 13.25 | 276 | 2560:80:32:80:20 (20) (2) |
PCIe 4.0 x8 |
2 | 1552 | 1777 | 14000 | 8 | 224.0 | 128 | 49.6 59.86 |
124.2 142.2 |
7.95 9.01 |
0.124 0.142 |
7.95 9.01 |
63.6 72.8 |
18.2 | 130 | No | $249 | — | |||||
GeForce RTX 3060[66] | October 27, 2022[67] | GA106-302 | 3584:112:48:112:28 (28) (3) |
PCIe 4.0 x16 |
1320 | 1777 | 15000 | 63.4 85.3 |
147.8 199.0 |
9.46 12.74 |
0.148 0.199 |
9.46 12.74 |
75.7 101.9 |
25 | 170 | $329 | ||||||||||||
February 25, 2021 | GA106-300-A1 | 3 | 12 | 360.0 | 192 | |||||||||||||||||||||||
September 1, 2021 | GA104-150-A1[68] | 17.4 | 392.5 | |||||||||||||||||||||||||
GeForce RTX 3060 Ti[69] | December 2, 2020 | GA104-200-A1 | 4864:152:80:152:38 (38) (5) |
4 | 1410 | 1665 | 14000 | 8 | 448.0 | 256 | 112.8 133.2 |
214.3 253.1 |
13.72 16.20 |
0.214 0.253 |
13.70 16.20 |
109.7 129.6 |
32.4 | 200 | $399 | |||||||||
October 27, 2022[70] | GA104-202 | 19000 | 608.0 | GDDR6X | ||||||||||||||||||||||||
GeForce RTX 3070[71][72] | October 29, 2020[73] | GA104-300-A1 | 5888:184:96:184:46 (46) (6) |
1500 | 1725 | 14000 | 448.0 | GDDR6 | 144.0 165.6 |
276.0 317.4 |
17.66 20.31 |
0.276 0.318 |
17.66 20.37 |
141.31 162.98 |
40.6 | $499 | ||||||||||||
GeForce RTX 3070 Ti[74] | June 10, 2021 | GA104-400-A1 | 6144:192:96:192:48 (48) (6) |
1575 | 1770 | 19000 | 608.3 | GDDR6X | 151.18 169.9 |
302.36 339.8 |
19.35 21.75 |
0.302 0.340 |
19.35 21.75 |
154.8 174.0 |
43.5 | 290 | $599 | |||||||||||
GeForce RTX 3080[75][72] | September 17, 2020 | GA102-200-A1 | 28.3 | 628.4 | 8704:272:96:272:68 (68) (6) |
5 | 1440 | 1710 | 10 | 760.0 | 320 | 138.2 164.2 |
391.68 465.12 |
25.07 29.77 |
0.392 0.465 |
25.06 29.76 |
200.54 238.14 |
59.5 | 320 | $699 | ||||||||
January 27, 2022 | GA102-220-A1 | 8960:280:96:280:70 (70) (6) |
6 | 1260 | 1710 | 12 | 912.0 | 384 | 131.0 177.8 |
352.8 478.8 |
22.6 30.6 |
0.353 0.479 |
22.6 30.6 |
180.6 245.1 |
61.3 | 350 | $799 | |||||||||||
GeForce RTX 3080 Ti[76] | June 3, 2021 | GA102-225-A1 | 10240:320:112:320:80 (80) (7) |
1365 | 1665 | 153.5 186.5 |
438.5 532.8 |
28.57 34.71 |
0.438 0.533 |
28.06 34.10 |
228.6 272.8 |
68.2 | $1199 | |||||||||||||||
GeForce RTX 3090[77][72] | September 24, 2020 | GA102-300-A1 | 10496:328:112:328:82 (82) (7) |
1395 | 1695 | 19500 | 24 | 935.8 | 156.2 189.8 |
457.6 555.96 |
29.28 35.58 |
0.459 0.558 |
29.38 35.68 |
235.08 285.48 |
71.1 | 2-way NVLink | $1499 | |||||||||||
GeForce RTX 3090 Ti[78][79] | March 29, 2022 | GA102-350-A1 | 10752:336:112:336:84 (84) (7) |
1560 | 1860 | 21000 | 1008.3 | 174.7 208.3 |
524.2 625 |
33.5 40 |
0.524 0.625 |
33.5 40 |
269.1 320.9 |
79.9 | 450 | $1999 |
- ^ Main shader processors : texture mapping unit : render output units : tensor cores : ray-tracing cores (streaming multiprocessors) (graphics processing clusters)
GeForce 40 series
- Supported APIs: Direct3D 12 Ultimate (12_2), OpenGL 4.6, OpenCL 3.0, Vulkan 1.3 and CUDA 8.9[80]
- Supported display connections: HDMI 2.1, DisplayPort 1.4a
- Tensor core 4th gen
- RT core 3rd gen
- NVIDIA DLSS 3
- No NVLink support, Multi-GPU over PCIe 5.0[81]
Model | Launch | Code name | Process | Transistors (billion) | Die size (mm2) | Core config[a] | Bus interface | L2 Cache (MB) | Clock speeds | Memory | Fillrate | Processing power (TFLOPS) | Ray-tracing Performance | TDP (Watts) | Release price (USD) | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) | Boost core clock (MHz) | Memory (MT/s) | Size (GB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Pixel (GP/s) | Texture (GT/s) | Single precision | Double precision | Half precision | Tensor compute (FP16) (2:1 sparse) | Rays/s (Billions) | RTX OPS/s (Trillions) | Ray Perf TFLOPS | MSRP | Founders Edition | ||||||||||
GeForce RTX 4070 Ti[82] | January 5, 2023 | AD104-400 | TSMC N4 | 35.8 | 294.5 | 7680:240:80:240:60 (60)(5) |
PCIe 4.0 x16 | 48 | 2310 | 2610 | 21000 | 12 | 504 | GDDR6X | 192 | 208.8 | 626.4 | 35.5 40.1 |
0.554 0.627 |
35.5 40.1 |
142 (284) 160 (321) |
92.7 | 285 | $799 | — | ||
GeForce RTX 4080[83] | Unlaunched [84][85] | $899 | |||||||||||||||||||||||||
November 16, 2022 | AD103-300 | 45.9 | 378.6 | 9728:304:112:304:76 (76)(7) |
64 | 2210 | 2505 | 22400 | 16 | 717 | 256 | 280.6 | 761.5 | 43.0 48.8 |
0.672 0.761 |
43.0 48.8 |
172 (344) 195 (390) |
112.7 | 320 | $1199 | |||||||
GeForce RTX 4090[86][87] | October 12, 2022 | AD102-300 | 76.3 | 608.5 | 16384:512:176:512:128 (128)(11) |
72 | 2230 | 2520 | 21000 | 24 | 1008 | 384 | 443.5 | 1290.2 | 73.1 82.6 |
1.142 1.291 |
73.1 82.6 |
292 (585) 330 (661) |
191 | 450 | $1599 |
- ^ Main shader processors : texture mapping unit : render output units : tensor cores : ray-tracing cores (streaming multiprocessors) (graphics processing clusters)
- ^ a b c d e f "The Khronos Group". 31 May 2022.
- ^ "Sprout Pro by HP". HP. Archived from the original on 2019-01-09. Retrieved 2019-01-09.
- ^ "Linux, Solaris, and FreeBSD driver 361.28 (long-lived branch release)". Nvidia. 2016-02-09. Archived from the original on 2016-02-16. Retrieved 2016-02-10.
- ^ "NVIDIA GeForce 945A Specs". Retrieved 2018-08-06.[dead link ]
- ^ "GTX 950 | Specifications". GeForce. Archived from the original on 2015-12-12. Retrieved 2015-12-11.
- ^ "GIGABYTE Adds 75W GeForce GTX 950 to Lineup".
- ^ "GeForce GTX 950 (OEM) | Specifications | GeForce". geforce.com. Archived from the original on 2018-09-23. Retrieved 2019-01-09.
- ^ "GTX 960 | Specifications". GeForce. Archived from the original on 2015-12-12. Retrieved 2015-12-11.
- ^ "Nvidia GeForce GTX 960 2GB vs 4GB review". Eurogamer. 18 October 2015.
- ^ "GeForce GTX 960 (OEM) | Specifications | GeForce". geforce.com. Archived from the original on 2018-09-23. Retrieved 2019-01-09.
- ^ "GTX 970 | Specifications". GeForce. Archived from the original on 2015-12-07. Retrieved 2015-12-11.
- ^ Wasson, Scott (January 26, 2015). "Nvidia: the GeForce GTX 970 works exactly as intended, A look inside the card's unusual memory config". The Tech Report. p. 1. Archived from the original on January 28, 2015. Retrieved 2015-01-26.
- ^ "GTX 980 | Specifications". GeForce. Archived from the original on 2015-12-08. Retrieved 2015-12-11.
- ^ "GTX 980 Ti | Specifications". GeForce. Archived from the original on 2015-12-11. Retrieved 2015-12-11.
- ^ "GTX TITAN X | Specifications". GeForce. Archived from the original on 2015-12-05. Retrieved 2015-12-11.
- ^ Nvidia. "GTX 1080 Graphics Card". Archived from the original on May 7, 2016. Retrieved May 7, 2016.
- ^ a b Smith, Ryan. "The Nvidia GeForce GTX 1080 & GTX 1070 Founders Editions Review: Kicking Off the FinFET Generation". Archived from the original on 2016-07-23. Retrieved 2016-07-21.
- ^ a b "The GeForce GTX 1060 Founders Edition & ASUS Strix GTX 1060 Review". Archived from the original on 2017-02-18. Retrieved 2017-02-17.
- ^ "NVIDIA GeForce GT 1010 Specs". TechPowerUp. Retrieved 2021-02-14.
- ^ "GeForce GT 1030 | Specifications | GeForce". Archived from the original on 2017-05-20. Retrieved 2017-05-17.
- ^ "GeForce GT 1030: The DDR4 Abomination Benchmarked". Archived from the original on 2018-08-22. Retrieved 2018-08-22.
- ^ "::Palit Products - GeForce GT 1030 ::". Archived from the original on 2017-06-14. Retrieved 2017-05-26.
- ^ "Overview GeForce GT 1030 AERO ITX 2G OC". Archived from the original on 2017-06-30. Retrieved 2017-05-26.
- ^ a b "GeForce GTX 1050 Graphics Card". nvidia.com. Archived from the original on 2016-12-22. Retrieved 2018-12-27.
- ^ "GTX 1060 Graphics Card". nvidia.com. Archived from the original on August 16, 2016. Retrieved August 18, 2016.
- ^ "NVIDIA Preps Cut Down, 5 GB GTX 1060 Graphics Card For Cafes". wccftech.com. 26 December 2017. Archived from the original on 2018-12-20. Retrieved 2018-12-29.
- ^ "NVIDIA launches GeForce GTX 1080 11 Gbps and GTX 1060 9 Gbps". videocardz.com. 20 April 2017. Archived from the original on 2018-09-02. Retrieved 2018-12-29.
- ^ "Gigabyte may be readying a GeForce GTX 1060 with GDDR5X". hexus.net. 19 October 2018. Archived from the original on 2018-12-30. Retrieved 2018-12-29.
- ^ a b "GEFORCE GTX 1070 FAMILY". nvidia.com. Archived from the original on 2017-10-27. Retrieved 2018-12-29.
- ^ "NVIDIA Unveils GeForce GTX 1070 with GDDR5X Memory". techpowerup.com. Archived from the original on 2018-12-30. Retrieved 2018-12-29.
- ^ W1zzard (May 17, 2016). "Nvidia GeForce GTX 1080 8 GB". TechPowerUp. Archived from the original on May 21, 2016. Retrieved May 17, 2016.
{{cite web}}
: CS1 maint: numeric names: authors list (link) - ^ W1zzard (June 21, 2016). "Nvidia GeForce GTX 1080 SLI". TechPowerUp. Archived from the original on June 24, 2016. Retrieved June 21, 2016.
{{cite web}}
: CS1 maint: numeric names: authors list (link) - ^ a b c "No, There Was No GeForce GTX 1070 Price Cut! - Tech ARP". www.techarp.com. 2 November 2017. Archived from the original on 2017-11-07. Retrieved 2017-11-05.
- ^ Nvidia. "GTX 1080 Graphics Card". Archived from the original on December 22, 2016. Retrieved May 7, 2016.
- ^ Nvidia. "GeForce GTX 1080 Ti Graphics Card". Archived from the original on March 1, 2017. Retrieved March 1, 2017.
- ^ Nvidia. "Nvidia TITAN X Graphics Card". Archived from the original on July 22, 2016. Retrieved July 21, 2016.
- ^ Nvidia. "TITAN Xp Graphics Card with Pascal Architecture". Archived from the original on April 6, 2017. Retrieved April 6, 2017.
- ^ Nvidia. "Nvidia TITAN V Graphics Card". Archived from the original on December 8, 2017. Retrieved December 8, 2017.
- ^ Smith, Ryan. "NVIDIA Unveils & Gives Away New Limited Edition 32GB Titan V "CEO Edition"". Archived from the original on 2018-07-30. Retrieved 2018-08-08.
- ^ "NVIDIA TITAN V - CEO Edition". TechPowerUp. Retrieved 2018-08-08.[dead link ]
- ^ "NVIDIA officially launches GeForce GTX 1630 graphics card". VideoCardz.com. Retrieved 2022-06-28.
- ^ "NVIDIA GeForce GTX 1650 Graphics Card". NVIDIA. Archived from the original on 2019-04-23. Retrieved 2019-04-23.
- ^ "NVIDIA's GeForce GTX 1650 GDDR6 Released: GDDR6 Reaching Price Parity With GDDR5". Anandtech. Retrieved 2020-04-06.
- ^ "NVIDIA GeForce GTX 1650 TU106 Specs". TechPowerUp. Retrieved 2021-12-14.
- ^ "NVIDIA GeForce GTX 1650 SUPER Graphics Card". NVIDIA. Retrieved 2019-10-29.
- ^ "NVIDIA Announces GeForce GTX 1650 Super: Launching November 22nd". Retrieved 2019-10-29.
- ^ "GTX 1660, 1650 Super boost speeds for Nvidia's cheapest gaming cards". Retrieved 2019-10-29.
- ^ "The GeForce 16 Series Graphics Cards are Here". NVIDIA. Archived from the original on 2019-03-25. Retrieved 2019-03-23.
- ^ "NVIDIA GeForce GTX 1660 SUPER Graphics Card". NVIDIA. Retrieved 2019-10-29.
- ^ "NVIDIA GeForce RTX 1660 Graphics Card". NVIDIA. Archived from the original on 2019-02-22. Retrieved 2019-02-22.
- ^ "NVIDIA GeForce RTX 2060 Graphics Card". NVIDIA. Archived from the original on 2019-01-07. Retrieved 2019-01-08.
- ^ "NVIDIA GeForce RTX 2060 TU104 Specs". TechPowerUp. Retrieved 2020-02-18.
- ^ "NVIDIA launches GeForce RTX 2060 with 12GB and TU106-300 GPU, overpriced gaming GPU for miners". videocardz. Retrieved 2021-07-09.
- ^ a b c "The GeForce RTX 2070 Super & RTX 2060 Super Review". Anandtech. 2019-07-02. Archived from the original on 2019-07-02. Retrieved 2019-07-02.
- ^ "Your Graphics, Now with SUPER Powers". Archived from the original on 2019-07-02. Retrieved 2019-07-02.
- ^ "Introducing NVIDIA GeForce RTX 2070 Graphics Card". NVIDIA. Archived from the original on 2018-08-20. Retrieved 2018-08-20.
- ^ "Nvidia Turing architecture deep dive". pcgamer.com. Archived from the original on 2018-09-18. Retrieved 2018-09-27.
- ^ "Your Graphics, Now with SUPER Powers". Archived from the original on 2019-07-02. Retrieved 2019-07-02.
- ^ "NVIDIA GeForce RTX 2080 Founders Edition Graphics Card". NVIDIA. Archived from the original on 2018-08-20. Retrieved 2018-08-20.
- ^ "Nvidia Can Automatically Overclock Your GeForce RTX in 20 Minutes". PCmag.com. Archived from the original on 2018-09-20. Retrieved 2018-09-20.
- ^ "Your Graphics, Now with SUPER Powers". Archived from the original on 2019-07-02. Retrieved 2019-07-02.
- ^ "Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card". NVIDIA. Archived from the original on 2018-08-20. Retrieved 2018-08-20.
- ^ "TITAN RTX Ultimate PC Graphics Card with Turing: NVIDIA". nvidia.com. Archived from the original on 2018-12-26. Retrieved 2018-12-27.
- ^ "NVIDIA GeForce RTX 3050 Graphics Card Announcement". NVIDIA (in Finnish). Retrieved 2022-01-04.
- ^ "NVIDIA Announces the GeForce RTX 30 Series". Mugens-Reviews (in German). Retrieved 2022-01-06.
- ^ "NVIDIA GeForce RTX 3060 Graphics Card Announcement". NVIDIA. Retrieved 2021-01-12.
- ^ "NVIDIA officially introduces GeForce RTX 3060 8GB and RTX 3060 Ti GDDR6X". VideoCardz.com. Retrieved 2022-10-29.
- ^ Mujtaba, Hassan (2021-09-25). "Custom GALAX & Gainward GeForce RTX 3060 Cards With NVIDIA Ampere GA104 GPUs Listed". Wccftech. Retrieved 2021-09-25.
- ^ "NVIDIA GeForce RTX 3060 Ti Graphics Card". Retrieved 2020-12-01.
- ^ "NVIDIA officially introduces GeForce RTX 3060 8GB and RTX 3060 Ti GDDR6X". VideoCardz.com. Retrieved 2022-10-29.
- ^ "NVIDIA GeForce RTX 3070 Graphics Card". NVIDIA. Retrieved 2020-09-06.
- ^ a b c Smith, Ryan (September 1, 2020). "NVIDIA Announces the GeForce RTX 30 Series: Ampere For Gaming, Starting With RTX 3080 & RTX 3090". AnandTech. Retrieved 2020-09-02.
- ^ "GeForce RTX 3070 Availability Update". NVIDIA.
- ^ "NVIDIA GeForce RTX 3070 Family". NVIDIA. Retrieved 2021-06-02.
- ^ "NVIDIA GeForce RTX 3080 Graphics Card". NVIDIA. Retrieved 2020-09-06.
- ^ "NVIDIA GeForce RTX 3080 Family of Graphics Card". NVIDIA. Retrieved 2021-06-02.
- ^ "NVIDIA GeForce RTX 3090 Graphics Card". NVIDIA. Retrieved 2020-09-06.
- ^ "GeForce RTX 3090 Ti Is Here: The Fastest GeForce GPU For The Most Demanding Creators & Gamers". NVIDIA. Retrieved 2022-04-02.
- ^ "NVIDIA GeForce RTX 3090 Ti Specs". TechPowerUp. Retrieved 2022-04-02.
- ^ "CUDA C++ Programming Guide". docs.nvidia.com. Retrieved 2022-09-20.
- ^ published, Chuong Nguyen (2022-09-21). "Nvidia kills off NVLink on RTX 4090". Windows Central. Retrieved 2023-01-01.
- ^ "NVIDIA 'accidentally' confirms GeForce RTX 4070 Ti GPU specifications". VideoCardz. 2022-12-30. Retrieved 2022-12-31.
- ^ "NVIDIA GeForce RTX 4080 Graphics Cards". NVIDIA. Retrieved 2022-09-20.
- ^ Warren, Tom (2022-10-14). "Nvidia says it's "unlaunching" the 12GB RTX 4080 after backlash". The Verge. Retrieved 2022-10-14.
- ^ "Unlaunching The 12GB 4080". NVIDIA. Retrieved 2022-10-14.
- ^ "NVIDIA GeForce RTX 4090 Graphics Cards". NVIDIA. Retrieved 2022-09-20.
- ^ "NVIDIA Ada GPU Architecture" (PDF). Retrieved October 8, 2022.