18- Nvidia Geforce GT 440 (2011)
The GeForce GT 440 was an entry-level graphics card by NVIDIA, launched in February 2011. Built on the 40 nm process, and based on the GF108 graphics processor, in its GF108-400-A1 variant, the card supports DirectX 12.0. The GF108 graphics processor is an average sized chip with a die area of 116 mm² and 585 million transistors. It features 96 shading units, 16 texture mapping units and 4 ROPs. NVIDIA has placed 1,024 MB DDR3 memory on the card, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 810 MHz, memory is running at 900 MHz.
Being a single-slot card, the NVIDIA GeForce GT 440 does not require any additional power connector, its power draw is rated at 65 W maximum. Display outputs include: 1x DVI, 1x HDMI, 1x VGA. GeForce GT 440 is connected to the rest of the system using a PCIe 2.0 x16 interface. The card measures 145 mm in length, and features a single-slot cooling solution. Its price at launch was 79 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 400
Release Date: February 1st, 2011
Launch Price: $79 USD
P/N Code: 600-11070-0000
Board Model: NVIDIA P1070
Graphics Processing Unit
GPU Model: GF108-400 (GF108)
Architecture: Fermi
Fabrication Process: 40 nm
Die Size: 116 mm2
Transistors Count: 585M
Transistors Density: 5M TRAN/mm2
CUDAs: 96
SMXs: 2
GPCs: 1
TMUs: 16
ROPs: 4
Clocks
Base Clock: 810 MHz
Boost Clock: TBD
Memory Clock: 900 MHz
Effective Memory Clock: 1800 Mbps
Memory Configuration
Memory Size: 1024 MB
Memory Type: DDR3
Memory Bus Width: 128-bit
Memory Bandwidth: 28.8 GB/s
Physical
Interface: PCI-Express 2.0 x16
Width: 11.1 cm
Length: 14.48 cm
Height: 1-slot
Power Connectors: -
TDP/TBP: 65 W
Recommended PSU: 400 W
Maximum Temperature: 105 °C
Display Outputs
DVI-I DualLink: 1 ×
HDMI: 1 ×
VGA: 1 ×
API Support
DirectX: 12.0
Vulkan: -
OpenGL: 4.5
OpenCL: 1.1
Shader Model: 5.0
Performance
Pixel Fillrate: 3.2 GPixels/s
Texture Fillrate: 13 GTexel/s
SPFP Performance1: 55.5 GFLOPS
Performance per W: 2.4 GFLOPS/W
Performance per mm2: 1.3 GFLOPS/mm2
19- Nvidia Geforce GTX 460 (2010)
The GeForce GTX 460 was a performance graphics card by NVIDIA, launched in July 2010. Built on the 40 nm process, and based on the GF104 graphics processor, in its GF104-300-KB-A1 variant, the card supports DirectX 12.0. The GF104 graphics processor is a large chip with a die area of 332 mm² and 1,950 million transistors. It features 336 shading units, 56 texture mapping units and 32 ROPs. NVIDIA has placed 1,024 MB GDDR5 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 675 MHz, memory is running at 900 MHz.
Being a dual-slot card, its power draw is rated at 160 W maximum. Display outputs include: 2x DVI, 1x mini-HDMI. GeForce GTX 460 is connected to the rest of the system using a PCIe 2.0 x16 interface. The card measures 210 mm in length, and features a dual-slot cooling solution. Its price at launch was 229 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 400
Release Date: July 12th, 2010
Launch Price: $229 USD
PCB Code: 180-11041-1102
P/N Code: 600-11041-0010
Model: NVIDIA P1041 SKU 010
Graphics Processing Unit
GPU Model: GF104-300 (GF104)
Architecture: Fermi
Fabrication Process: 40 nm
Die Size: 332 mm2
Transistors Count: 2B
Transistors Density: 5.9M TRAN/mm2
CUDAs: 336
SMXs: 7
GPCs: 2
TMUs: 56
ROPs: 32
Clocks
Base Clock: 675 MHz
Boost Clock: TBD
Memory Clock: 900 MHz
Effective Memory Clock: 3600 Mbps
Memory Configuration
Memory Size: 1024 MB
Memory Type: GDDR5
Memory Bus Width: 256-bit
Memory Bandwidth: 115.2 GB/s
Physical
Interface: PCI-Express 2.0 x16
Width: 11.1 cm
Length: 21 cm
Height: 2-slot
Power Connectors: 2 × 6-pin
TDP/TBP: 160 W
Recommended PSU: 450 W
Maximum Temperature: 105 °C
Display Outputs
DVI-I DualLink: 2 ×
miniHDMI: 1 ×
API Support
DirectX: 12.0
Vulkan: -
OpenGL: 4.5
OpenCL: 1.1
Shader Model: 5.0
Performance
Pixel Fillrate: 21.6 GPixels/s
Texture Fillrate: 37.8 GTexel/s
SPFP Performance: 453.6 GFLOPS
Performance per W: 2.8 GFLOPS/W
Performance per mm2: 1.4 GFLOPS/mm2
20- Nvidia Geforce GTX 580 (2010)
The GeForce GTX 580 GPU delivers the world’s fastest performance for DirectX 11 (DX11) games, and support for NVIDIA 3D Vision, Surround, PhysX, SLI and CUDA technologies, further entrenching GeForce-based PCs as the most robust gaming platforms in the world. The combination of an innovative vapor chamber thermal solution and new architectural enhancements make the GTX 580 the fastest and quietest GPU in its class, delivering an increase of up to 35 percent in performance per watti, and performance that is up to 30 percent faster than the original GeForce GTX 480.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 500
Release Date: November 9th, 2010
Launch Price: $499 USD
PCB Code: 180-11261-1102
P/N Code: 600-11261-0002
S/N Code: P1261-A00
Model: NVIDIA P1261 SKU 002
Graphics Processing Unit
GPU Model: GF110-375 (GF110)
Architecture: Fermi
Fabrication Process: 40 nm
Die Size: 520 mm2
Transistors Count: 3.1B
Transistors Density: 5.9M TRAN/mm2
CUDAs: 512
SMXs: 16
GPCs: 4
TMUs: 64
ROPs: 48
Clocks
Base Clock: 772 MHz
Boost Clock: TBD
Memory Clock: 1002 MHz
Effective Memory Clock: 4008 Mbps
Memory Configuration
Memory Size: 1536 MB
Memory Type: GDDR5
Memory Bus Width: 384-bit
Memory Bandwidth: 192.4 GB/s
Physical
Interface: PCI-Express 2.0 x16
Width: 11.12 cm
Length: 26.67 cm
Height: 2-slot
Power Connectors: 1 × 6-pin, 1 × 8-pin
Power Design: 6+2
TDP/TBP: 244 W
Recommended PSU: 600 W
Maximum Temperature: 97 °C
Multi-GPU Support: 3-way
Display Outputs
DVI-D DualLink: 1 ×
DVI-I DualLink: 1 ×
miniHDMI: 1 ×
API Support
DirectX: 12.0
Vulkan: -
OpenGL: 4.5
OpenCL: 1.1
Shader Model: 5.0
Performance
Pixel Fillrate: 37.1 GPixels/s
Texture Fillrate: 49.4 GTexel/s
SPFP Performance: 790.5 GFLOPS
Performance per W: 3.2 GFLOPS/W
Performance per mm2: 1.5 GFLOPS/mm2
21- Nvidia Geforce GTX 650 (2012)
The GeForce GTX 660 and GeForce GTX 650 GPUs set a new benchmark for high-performance, remarkably-priced gaming when paired with the incredible line-up of top DirectX 11 games, including Call of Duty: Black Ops II, Assassin’s Creed III and World of Warcraft: Mists of Pandaria.
The GeForce GTX 660 represents a phenomenal upgrade opportunity for gamers still playing games on last-generation graphics technology. For the millions of gamers still gaming on the GeForce 9800 GT, the 4X performance improvementi delivered by the GTX 660 will be an upgrade temptation not easily resisted. Similarly, the GTX 650 delivers an 8X performance improvement over the 9500 GTii, allowing gamers to step up to the GTX family with a low-cost solution that delivers a significant boost in performance.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 600
Release Date: September 13th, 2012
Launch Price: $109 USD
P/N Code: 600-12010-0004
Model: NVIDIA P2010 SKU 004
Graphics Processing Unit
GPU Model: GK107-450 (GK107)
Architecture: Kepler
Fabrication Process: 28 nm
Die Size: 118 mm2
Transistors Count: 1.3B
Transistors Density: 11M TRAN/mm2
CUDA Cores: 384
SMMs: 2
GPCs: 1
TMUs: 32
ROPs: 16
Clocks
Base Clock: 1058 MHz
Boost Clock: TBD
Memory Clock: 1252 MHz
Effective Memory Clock: 5008 Mbps
Memory Configuration
Memory Size: 1024 MB
Memory Type: GDDR5
Memory Bus Width: 128-bit
Memory Bandwidth: 80.1 GB/s
Physical
Interface: PCI-Express 3.0 x16
Width: 11.12 cm
Length: 12.7 cm
Height: 1-slot
Power Connectors: 1 × 6-pin
Power Design: 2
TDP/TBP: 64 W
Recommended PSU: 400 W
Display Outputs
DVI-D DualLink: 1 ×
DVI-I DualLink: 1 ×
miniHDMI: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 2.0
Shader Model: 5.0
Performance
Pixel Fillrate: 16.9 GPixels/s
Texture Fillrate: 33.9 GTexel/s
SPFP Performance: 812.5 GFLOPS
Performance per W: 12.7 GFLOPS/W
Performance per mm2: 6.9 GFLOPS/mm2
22- Nvidia Geforce GTX 760 Ti (2013)
The GeForce GTX 760 Ti OEM is a graphics card by NVIDIA, launched in September 2013. Built on the 28 nm process, and based on the GK104 graphics processor, the card supports DirectX 12.0. The GK104 graphics processor is an average sized chip with a die area of 294 mm² and 3,540 million transistors. Unlike the fully unlocked GeForce GTX 680 Mac Edition, which uses the same GPU but has all 1536 shaders enabled, NVIDIA has disabled some shading units on the GeForce GTX 760 Ti OEM to reach the product's target shader count. It features 1344 shading units, 112 texture mapping units and 32 ROPs. NVIDIA has placed 2,048 MB GDDR5 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 915 MHz, which can be boosted up to 980 MHz, memory is running at 1502 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 760 Ti OEM draws power from 2x 6-pin power connectors, with power draw rated at 170 W maximum. Display outputs include: 2x DVI, 1x HDMI, 1x DisplayPort. GeForce GTX 760 Ti OEM is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 241 mm in length, and features a dual-slot cooling solution.
SPECS
Overview
Manufacturer: NVIDIA
Based on: GTX 670
Original Series: GeForce 700
Release Date: August 25th, 2013
Launch Price: OEM
Board Model: NVIDIA P2004
Graphics Processing Unit
GPU Model: GK104-325 (GK104)
Architecture: Kepler
Fabrication Process: 28 nm
Die Size: 294 mm2
Transistors Count: 3.5B
Transistors Density: 12M TRAN/mm2
CUDA Cores: 1344
SMMs: 7
GPCs: 4
TMUs: 112
ROPs: 32
Clocks
Base Clock: 915 MHz
Boost Clock: 980 MHz
Memory Clock: 1502 MHz
Effective Memory Clock: 6008 Mbps
Memory Configuration
Memory Size: 2048 MB
Memory Type: GDDR5
Memory Bus Width: 256-bit
Memory Bandwidth: 192.3 GB/s
Physical
Interface: PCI-Express 3.0 x16
Width: 11.12 cm
Length: 24.13 cm
Height: 2-slot
Power Connectors: 2 × 6-pin
Power Design: 4+2
TDP/TBP: 170 W
Recommended PSU: 500 W
Maximum Temperature: 97 °C
Multi-GPU Support: 4-way
Display Outputs
DVI-D DualLink: 1 ×
DVI-I DualLink: 1 ×
DisplayPort: 1 ×
HDMI: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 2.0
Shader Model: 5.0
Performance
Pixel Fillrate: 29.3 GPixels/s
Texture Fillrate: 102.5 GTexel/s
SPFP Performance: 2.5 TFLOPS
Performance per W: 14.5 GFLOPS/W
Performance per mm2: 8.4 GFLOPS/mm2
23- Nvidia Geforce GTX 750 Ti (2014)
The GeForce GTX 750 Ti is a mid-range graphics card by NVIDIA, launched in February 2014. Built on the 28 nm process, and based on the GM107 graphics processor, in its GM107-400-A2 variant, the card supports DirectX 12.0. The GM107 graphics processor is an average sized chip with a die area of 148 mm² and 1,870 million transistors. It features 640 shading units, 40 texture mapping units and 16 ROPs. NVIDIA has placed 2,048 MB GDDR5 memory on the card, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 1020 MHz, which can be boosted up to 1085 MHz, memory is running at 1350 MHz.
Being a single-slot card, the NVIDIA GeForce GTX 750 Ti does not require any additional power connector, its power draw is rated at 60 W maximum. Display outputs include: 2x DVI, 1x mini-HDMI. GeForce GTX 750 Ti is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 145 mm in length, and features a single-slot cooling solution. Its price at launch was 149 US Dollars.
SPECS
Overview
Card Status: Released
Manufacturer: NVIDIA
Release Date: 18th February, 2014
Launch Price: $149 USD
Board Model: NVIDIA P2010
GPU
GPU Model: 28nm GM107-400
Cores : TMUs : ROPs: 640 : 40 : 16
Clocks
Base Clock: 1020 MHz
Boost Clock: 1085 MHz
Memory Clock (Effective): 1350 (5400) MHz
Computing Power: (FP32)1,306 GFLOPS
Memory
Memory Size: 2048 MB GDDR5
Memory Bus Width: 128-bit
Memory Bandwidth: 86.4 GB/s
Physical
Interface: PCI-Express 3.0 x16
Thermal Design Power: 60 W
24- Nvidia Geforce GTX 980ti (2015)
The GeForce GTX 980 Ti is a high-end graphics card by NVIDIA, launched in June 2015. Built on the 28 nm process, and based on the GM200 graphics processor, in its GM200-310-A1 variant, the card supports DirectX 12.0. The GM200 graphics processor is a large chip with a die area of 601 mm² and 8,000 million transistors. Unlike the fully unlocked GeForce GTX TITAN X, which uses the same GPU but has all 3072 shaders enabled, NVIDIA has disabled some shading units on the GeForce GTX 980 Ti to reach the product's target shader count. It features 2816 shading units, 176 texture mapping units and 96 ROPs. NVIDIA has placed 6,144 MB GDDR5 memory on the card, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 1000 MHz, which can be boosted up to 1076 MHz, memory is running at 1753 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 980 Ti draws power from 1x 6-pin + 1x 8-pin power connectors, with power draw rated at 250 W maximum. Display outputs include: 1x DVI, 1x HDMI, 3x DisplayPort. GeForce GTX 980 Ti is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 649 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 900
Release Date: June 1st, 2015
Launch Price: $649 USD
PCB Code: 180-1G600-CAAA
P/N Code: 699-1G600-0030
Model: NVIDIA PG600 SKU 030
Graphics Processing Unit
GPU Model: GM200-310 (GM200)
Architecture: Maxwell
Fabrication Process: 28 nm
Die Size: 601 mm2
Transistors Count: 8B
Transistors Density: 13.3M TRAN/mm2
CUDA Cores: 2816
SMMs: 22
GPCs: 6
TMUs: 172
ROPs: 96
Clocks
Base Clock: 1000 MHz
Boost Clock: 1076 MHz
Memory Clock: 1750 MHz
Effective Memory Clock: 7000 Mbps
Memory Configuration
Memory Size: 6144 MB
Memory Type: GDDR5
Memory Bus Width: 384-bit
Memory Bandwidth: 336 GB/s
Physical
Interface: PCI-Express 3.0 x16
Height: 2-slot
Power Connectors: 1 × 6-pin, 1 × 8-pin
TDP/TBP: 250 W
Recommended PSU: 600 W
Multi-GPU Support: 3-way
Display Outputs
DVI-I DualLink: 1 ×
DisplayPort: 3 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.1
Shader Model: 5.0
Performance
Pixel Fillrate: 96 GPixels/s
Texture Fillrate: 172 GTexel/s
SPFP Performance: 5.6 TFLOPS
Performance per W: 22.5 GFLOPS/W
Performance per mm2: 9.4 GFLOPS/mm2
25- Nvidia Geforce GTX 1050 Ti (2016)
The GeForce GTX 1050 Ti is a mid-range graphics card by NVIDIA, launched in October 2016. Built on the 14 nm process, and based on the GP107 graphics processor, in its GP107-400-A1 variant, the card supports DirectX 12.0. The GP107 graphics processor is an average sized chip with a die area of 132 mm² and 3,300 million transistors. It features 768 shading units, 48 texture mapping units and 32 ROPs. NVIDIA has placed 4,096 MB GDDR5 memory on the card, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 1291 MHz, which can be boosted up to 1392 MHz, memory is running at 1752 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 1050 Ti does not require any additional power connector, its power draw is rated at 75 W maximum. Display outputs include: 1x DVI, 1x HDMI, 1x DisplayPort. GeForce GTX 1050 Ti is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 145 mm in length, and features a dual-slot cooling solution. Its price at launch was 139 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 10
Release Date: October 25th, 2016
Launch Price: $139 USD
P/N Code: 699-1G210-0000-200
Device: ID1C82
Board Model: NVIDIA PG210
Graphics Processing Unit
GPU Model: GP107-400 (GP107)
Architecture: Pascal
Fabrication Process: 14 nm FinFET
Die Size: 132 mm2
Transistors Count: 3.3B
Transistors Density: 25M TRAN/mm2
CUDAs: 768
SMP: 12
TMUs: 48
ROPs: 32
Clocks
Base Clock: 1290 MHz
Boost Clock: 1392 MHz
Memory Clock: 1750 MHz
Effective Memory Clock: 7000 Mbps
Memory Configuration
Memory Size: 4096 MB
Memory Type: GDDR5
Memory Bus Width: 128-bit
Memory Bandwidth: 112 GB/s
Physical
Interface: PCI-Express 3.0 x16
Power Connectors: -
TDP/TBP: 75 W
Recommended PSU: 300 W
Maximum Temperature: 97 °C
Multi-GPU Support: Unsupported
Display Outputs
DVI-D DualLink: 1 ×
DisplayPort: 1 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.2
Shader Model: 5.0
Performance
Pixel Fillrate: 41.3 GPixels/s
Texture Fillrate: 61.9 GTexel/s
SPFP Performance: 2 TFLOPS
Performance per W: 26.4 GFLOPS/W
Performance per mm2: 15 GFLOPS/mm2
26- Nvidia Geforce GT 1030 (2017)
The GeForce GT 1030 is an entry-level graphics card by NVIDIA, launched in May 2017. Built on the 14 nm process, and based on the GP108 graphics processor, in its GP108-300-A1 variant, the card supports DirectX 12.0. The GP108 graphics processor is a relatively small chip with a die area of only 74 mm² and 1,800 million transistors. It features 384 shading units, 24 texture mapping units and 16 ROPs. NVIDIA has placed 2,048 MB GDDR5 memory on the card, which are connected using a 64-bit memory interface. The GPU is operating at a frequency of 1228 MHz, which can be boosted up to 1468 MHz, memory is running at 1502 MHz.
Being a single-slot card, the NVIDIA GeForce GT 1030 does not require any additional power connector, its power draw is rated at 30 W maximum. Display outputs include: 1x DVI, 1x HDMI. GeForce GT 1030 is connected to the rest of the system using a PCIe 3.0 x4 interface. The card measures 145 mm in length, and features a single-slot cooling solution. Its price at launch was 79 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 10
Release Date: May 17th, 2017
Launch Price: $79 USD
Device: ID1D01
Graphics Processing Unit
GPU Model: GP108-300 (GP108)
Architecture: Pascal
Fabrication Process: 16 nm FinFET
CUDAs: 384
TMUs: 24
ROPs: 8
Clocks
Base Clock: 1227 MHz
Boost Clock: 1468 MHz
Memory Clock: 1500 MHz
Effective Memory Clock: 6000 Mbps
Memory Configuration
Memory Size: 2048 MB
Memory Type: GDDR5
Memory Bus Width: 64-bit
Memory Bandwidth: 48 GB/s
Physical
Interface: PCI-Express 3.0 x16
Height: 1-slot
Low Profile: Yes
Power Connectors: -
TDP/TBP: 30 W
Recommended PSU: 300 W
Display Outputs
DVI-D DualLink: 1 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.2
Shader Model: 5.0
Performance
Pixel Fillrate: 9.8 GPixels/s
Texture Fillrate: 29.4 GTexel/s
SPFP Performance: 942.3 GFLOPS
Performance per W: 31.4 GFLOPS/W
27- Nvidia Geforce GTX 1060 (2016)
The GeForce GTX 1060 6 GB is a performance graphics card by NVIDIA, launched in July 2016. Built on the 16 nm process, and based on the GP106 graphics processor, in its GP106-400-A1 variant, the card supports DirectX 12.0. The GP106 graphics processor is an average sized chip with a die area of 200 mm² and 4,400 million transistors. It features 1280 shading units, 80 texture mapping units and 48 ROPs. NVIDIA has placed 6,144 MB GDDR5 memory on the card, which are connected using a 192-bit memory interface. The GPU is operating at a frequency of 1506 MHz, which can be boosted up to 1709 MHz, memory is running at 2002 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 1060 6 GB draws power from 1x 6-pin power connectors, with power draw rated at 120 W maximum. Display outputs include: 1x DVI, 1x HDMI, 3x DisplayPort. GeForce GTX 1060 6 GB is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 250 mm in length, and features a dual-slot cooling solution. Its price at launch was 299 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 10
Release Date: July 19th, 2016
Launch Price: $249 USD
P/N Code: 699-1G410-0030
S/N Code: PG410-A01
Device: ID1C03
Model: NVIDIA PG410 SKU 030
Graphics Processing Unit
GPU Model: GP106-400 (GP106)
Architecture: Pascal
Fabrication Process: 16 nm FinFET
Die Size: 200 mm2
Transistors Count: 4.4B
Transistors Density: 22M TRAN/mm2
CUDAs: 1280
SMP: 20
TMUs: 80
ROPs: 48
Clocks
Base Clock: 1506 MHz
Boost Clock: 1708 MHz
Memory Clock: 2000 MHz
Effective Memory Clock: 8000 Mbps
Memory Configuration
Memory Size: 6144 MB
Memory Type: GDDR5
Memory Bus Width: 192-bit
Memory Bandwidth: 192 GB/s
Physical
Interface: PCI-Express 3.0 x16
Height: 2-slot
Power Connectors: 1 × 6-pin
TDP/TBP: 120 W
Recommended PSU: 450 W
Maximum Temperature: 94 °C
Multi-GPU Support: Unsupported
Display Outputs
DVI-I DualLink: 1 ×
DisplayPort: 1 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.2
Shader Model: 5.0
Performance
Pixel Fillrate: 72.3 GPixels/s
Texture Fillrate: 120.5 GTexel/s
SPFP Performance: 3.9 TFLOPS
Performance per W: 32.1 GFLOPS/W
Performance per mm2: 19.3 GFLOPS/mm2
28- Nvidia Geforce GTX 1070 Ti (2017)
The GeForce GTX 1070 Ti is a high-end graphics card by NVIDIA, launched in November 2017. Built on the 16 nm process, and based on the GP104 graphics processor, in its GP104-300-A1 variant, the card supports DirectX 12.0. The GP104 graphics processor is a large chip with a die area of 314 mm² and 7,200 million transistors. Unlike the fully unlocked GeForce GTX 1080, which uses the same GPU but has all 2560 shaders enabled, NVIDIA has disabled some shading units on the GeForce GTX 1070 Ti to reach the product's target shader count. It features 2432 shading units, 152 texture mapping units and 64 ROPs. NVIDIA has placed 8,192 MB GDDR5 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1607 MHz, which can be boosted up to 1683 MHz, memory is running at 2002 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 1070 Ti draws power from 1x 8-pin power connectors, with power draw rated at 180 W maximum. Display outputs include: 1x DVI, 1x HDMI, 3x DisplayPort. GeForce GTX 1070 Ti is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 399 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 10
Release Date: November 2nd, 2017
Launch Price: $449 USD
Board Model: NVIDIA PG411
Graphics Processing Unit
GPU Model: GP104-300 (GP104)
Architecture: Pascal
Fabrication Process: 16 nm FinFET
Die Size: 314 mm2
Transistors Count: 7.2B
Transistors Density: 22.9M TRAN/mm2
CUDAs: 2432
SMP: 19
TMUs: 152
ROPs: 64
Clocks
Base Clock: 1607 MHz
Boost Clock: 1683 MHz
Memory Clock: 2002 MHz
Effective Memory Clock: 8008 Mbps
Memory Configuration
Memory Size: 8192 MB
Memory Type: GDDR5
Memory Bus Width: 256-bit
Memory Bandwidth: 256.3 GB/s
Physical
Interface: PCI-Express 3.0 x16
Width: 11.16 cm
Length: 26.67 cm
Height: 2-slot
Power Connectors: 1 × 8-pin
TDP/TBP: 180 W
Recommended PSU: 500 W
Display Outputs
DVI-I DualLink: 1 ×
DisplayPort: 3 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.2
Shader Model: 5.0
Performance
Pixel Fillrate: 102.8 GPixels/s
Texture Fillrate: 244.3 GTexel/s
SPFP Performance: 7.8 TFLOPS
Performance per W: 43.4 GFLOPS/W
Performance per mm2: 24.9 GFLOPS/mm2
29- Nvidia Geforce GTX 1080 Ti (2017)
The GeForce GTX 1080 Ti is a high-end graphics card by NVIDIA, launched in March 2017. Built on the 16 nm process, and based on the GP102 graphics processor, in its GP102-350-K1-A1 variant, the card supports DirectX 12.0. The GP102 graphics processor is a large chip with a die area of 471 mm² and 12,000 million transistors. Unlike the fully unlocked TITAN Xp, which uses the same GPU but has all 3840 shaders enabled, NVIDIA has disabled some shading units on the GeForce GTX 1080 Ti to reach the product's target shader count. It features 3584 shading units, 224 texture mapping units and 88 ROPs. NVIDIA has placed 11,264 MB GDDR5X memory on the card, which are connected using a 352-bit memory interface. The GPU is operating at a frequency of 1481 MHz, which can be boosted up to 1582 MHz, memory is running at 1376 MHz.
Being a dual-slot card, the NVIDIA GeForce GTX 1080 Ti draws power from 1x 6-pin + 1x 8-pin power connectors, with power draw rated at 250 W maximum. Display outputs include: 1x HDMI, 3x DisplayPort. GeForce GTX 1080 Ti is connected to the rest of the system using a PCIe 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 699 US Dollars.
SPECS
Overview
Manufacturer: NVIDIA
Original Series: GeForce 10
Release Date: March 10th, 2017
Launch Price: $699 USD
PCB Code: 180-1G611-DAAA
P/N Code: 699-1G611-0010
Device: ID1B06
Model: NVIDIA PG611 SKU 010
Graphics Processing Unit
GPU Model: GP102-350 (GP102)
Architecture: Pascal
Fabrication Process: 16 nm FinFET
Die Size: 471 mm2
Transistors Count: 12B
Transistors Density: 25.5M TRAN/mm2
CUDAs: 3584
SMP: 28
TMUs: 224
ROPs: 88
Clocks
Base Clock: 1480 MHz
Boost Clock: 1582 MHz
Memory Clock: 1376 MHz
Effective Memory Clock: 11008 Mbps
Memory Configuration
Memory Size: 11264 MB
Memory Type: GDDR5X
Memory Bus Width: 352-bit
Memory Bandwidth: 484.4 GB/s
Physical
Interface: PCI-Express 3.0 x16
Width: 11.16 cm
Length: 26.67 cm
Height: 2-slot
Power Connectors: 1 × 6-pin, 1 × 8-pin
TDP/TBP: 250 W
Recommended PSU: 600 W
Maximum Temperature: 91 °C
Multi-GPU Support: 2-way
Display Outputs
DisplayPort: 3 ×
HDMI 2.0: 1 ×
API Support
DirectX: 12.0
Vulkan: 1.0
OpenGL: 4.5
OpenCL: 1.2
Shader Model: 5.0
Performance
Pixel Fillrate: 130.2 GPixels/s
Texture Fillrate: 331.5 GTexel/s
SPFP Performance: 10.6 TFLOPS
Performance per W: 42.4 GFLOPS/W
Performance per mm2: 22.5 GFLOPS/mm2
