Comparison of Nvidia graphics processing units

From Wikipedia, the free encyclopedia
  (Redirected from Nvidia gpu)
Jump to: navigation, search
For information on AMD (previously ATI) graphics processing units, see Comparison of AMD graphics processing units.

This page contains general information about Nvidia's GPUs and videocards based on official Nvidia specifications.

Contents

[edit] DirectX version note

DirectX version indicates which graphics acceleration operations the card supports.

  • DirectX 6.0 – Multitexturing
  • DirectX 7.0 – Hardware Transformation, Clipping and Lighting (TCL/T&L)
  • DirectX 8.0 – Pixel Shader 1.1 & Vertex Shader 1.1
  • DirectX 8.1 – Pixel Shader 1.4 & Vertex Shader 1.1
  • DirectX 9.0 – Shader Model 2.0
  • DirectX 9.0b – Pixel Shader 2.0b & Vertex Shader 2.0
  • DirectX 9.0c – Shader Model 3.0, GPGPU
  • DirectX 9.0L – Windows Vista only, Vista version of DirectX 9.0c, Shader Model 3.0, Windows Graphics Foundation 1.0, DXVA 1.0, GPGPU
  • Direct3D 10 – Windows Vista/Windows 7, Shader Model 4.0, Windows Graphics Foundation 2.0, DXVA 2.0, GPGPU
  • Direct3D 10.1 – Windows Vista SP1/Windows 7, Shader Model 4.1, Windows Graphics Foundation 2.1, DXVA 2.1, GPGPU
  • Direct3D 11 – Windows Vista (With Patch)/Windows 7, Shader Model 5.0, Tessellation, Multithreaded rendering, Compute shaders, supported by hardware and software running Direct3D 9/10/10.1, GPGPU
  • Direct3D 11.1 – Windows 8, Stereoscopic 3D Rendering, GPGPU

[edit] OpenGL version note

OpenGL version indicates which graphics acceleration operations the card supports.

  • OpenGL 1.1 - Texture objects
  • OpenGL 1.2 - 3D textures, BGRA and packed pixel formats[1]
  • OpenGL 1.3 - Multitexturing, multisampling, texture compression
  • OpenGL 1.4 - Depth textures
  • OpenGL 1.5 - VBO, Occlusion Queries[2]
  • OpenGL 2.0 - GLSL 1.1, MRT, Non Power of Two textures, Point Sprites, Two-sided stencil[2]
  • OpenGL 2.1 - GLSL 1.2, Pixel Buffer Object (PBO), sRGB Textures[2]
  • OpenGL 3.0 - GLSL 1.3, Texture Arrays, Conditional rendering, FBO[3]
  • OpenGL 3.1 - GLSL 1.4, Instancing, Texture Buffer Object, Uniform Buffer Object, Primitive restart[4]
  • OpenGL 3.2 - GLSL 1.5, Geometry Shader, Multi-sampled textures[5]
  • OpenGL 3.3 - GLSL 3.30 Backports as much functionality possible from the OpenGL 4.0 specification
  • OpenGL 4.0 - GLSL 4.00 Tessellation on GPU, shaders with 64-bit precision
  • OpenGL 4.1 - GLSL 4.10 Developer-friendly debug outputs, compatibility with OpenGL ES 2.0
  • OpenGL 4.2 - GLSL 4.20 Shaders with atomic counters, transform feedback, shader packing, performance improvements

[edit] Field explanations

The fields in the table listed below describe the following:

  • Model - The marketing name for the processor assigned by Nvidia.
  • Launch - Date of release for the processor.
  • Code name - The internal engineering codename for the processor (typically designated by an NVXY name and later GXY where X is the series number and Y is the schedule of the project for that generation).
  • Fab - Fabrication process. Average feature size of components of the processor.
  • Bus interface - Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCI-Express).
  • Memory - The amount of graphics memory available to the processor.
  • Core clock - The factory core clock frequency (while some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by Nvidia).
  • Memory clock - The factory effective memory clock frequency (while some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by Nvidia). All DDR/GDDR memories operate at half this frequency, except for GDDR5, which operates at one quarter of this frequency.
  • Config core - The layout of the graphics pipeline, in terms of functional units. Over time the number, type, and variety of functional units in the GPU core has changed significantly; before each section in the list there is an explanation as to what functional units are present in each generation of processors. In later models, shaders are integrated into a unified shader architecture, where any one shader can perform any of the functions listed.
  • Fillrate - Maximum theoretical fillrate in textured pixels per second. This number is generally used as a "maximum throughput number" for the GPU and generally, a higher fillrate corresponds to a more powerful (and faster) GPU.
  • Memory subsection
    • Bandwidth - Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GB=10^9 bytes.
    • Bus type - Type of memory bus or buses utilized.
    • Bus width - Maximum bit width of the memory bus or buses utilized. This will always be a factory bus width.
  • API support section
    • DirectX - Maximum version of DirectX fully supported.
    • OpenGL - Maximum version of OpenGL fully supported.
  • Features - Additional features that are not standard as a part of the two graphics libraries.

[edit] Comparison tables: desktop GPUs

[edit] Pre-GeForce

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
STG-2000 September 1995 NV1 350 PCI 2, 4 Unknown 75 Unknown Unknown Unknown 12 0 0.6 EDO/
VRAM		 64 n/a n/a
Riva128 April 1997 NV3 350 PCI 4 100 100 1:0:1:1 100 100 100 0 1.6 SDR 128 5.0 1.0
Riva128ZX February 23, 1998 NV3 350 AGP 1x 8 100 100 1:0:1:1 100 100 100 0 1.6 SDR 128 5.0 1.0
Riva TNT March 23, 1998 NV4 350 AGP 2x 8, 16 90 110 2:0:2:2 180 180 180 0 1.76 SDR 128 5.0 1.0
Riva TNT2 Vanta LT March 8, 2000 NV6 250 AGP 4x 16 80 100 2:0:2:2 160 160 160 0 0.8 SDR 64 6.0 1.0
Riva TNT2 Vanta October 1999 NV6 250 AGP 4x 32 100 125 2:0:2:2 200 200 200 0 1 SDR 64 6.0 1.0
Riva TNT2 M64 July 1999 NV6 250 AGP 4x 16 125 150 2:0:2:2 250 250 250 0 1.2 SDR 64 6.0 1.0
Riva TNT2 March 15, 1999 NV5 250 AGP 4x 16, 32 125 150 2:0:2:2 250 250 250 0 2.4 SDR 128 6.0 1.0
Riva TNT2 Pro October 12, 1999 NV5 250 AGP 4x 32 143 166 2:0:2:2 286 286 286 0 2.656 SDR 128 6.0 1.0
Riva TNT2 Ultra March 15, 1999 NV5 250 AGP 4x 16, 32 150 183 2:0:2:2 300 300 300 0 2.928 SDR 128 6.0 1.0

[edit] GeForce256 series

Main article: GeForce 256
  • All models are manufactured with a 220 nm fabrication process
  • All models support DirectX 7.0 and OpenGL 1.2
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce256 October 11, 1999 NV10 AGP 4x, PCI 32, 64 120 166 4:0:4:4 480 480 480 0 2.656 SDR 128
GeForce256 DDR February 1, 2000 NV10 AGP 4x, PCI 32, 64 120 300 4:0:4:4 480 480 480 0 4.8 DDR 128

[edit] Features

Model Features
GPU Transform and Lighting (T&L) Cube Environment Mapping
GeForce256 Yes Yes Yes
GeForce256 DDR Yes Yes Yes

[edit] GeForce2 series

Main article: GeForce 2 Series
  • All models are manufactured with a 180 nm manufacturing process
  • All models support DirectX 7 and OpenGL 1.2
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce2 MX IGP + nForce 220/420 June 4, 2001 N/A FSB Up to 32 system RAM 175 266 2:0:4:2 350 350 700 0 2.128, 4.256 DDR 64/128
GeForce2 MX200 March 3, 2001 NV11 AGP 4x, PCI 32, 64 175 332 2:0:4:2 350 350 700 0 1.328 SDR 64
GeForce2 MX June 28, 2000 NV11 AGP 4x, PCI 32, 64 175 166 2:0:4:2 350 350 700 0 2.656 SDR 128
GeForce2 MX400 March 3, 2001 NV11 AGP 4x, PCI 32, 64 200 166 (SDR)
332 (DDR)		 2:0:4:2 400 400 800 0 2.656 SDR
DDR		 128 (SDR)
64 (DDR)
GeForce2 GTS April 26, 2000 NV15 AGP 4x, PCI 32, 64 200 332 4:0:8:4 800 800 1600 0 5.312 DDR 128
GeForce2 Pro December 5, 2000 NV15 AGP 4x, PCI 32, 64 200 400 4:0:8:4 800 800 1600 0 6.4 DDR 128
GeForce2 Ti October 1, 2001 NV15 AGP 4x, PCI 32, 64 250 400 4:0:8:4 1000 1000 2000 0 6.4 DDR 128
GeForce2 Ultra August 14, 2000 NV16 AGP 4x, PCI 64 250 460 4:0:8:4 1000 1000 2000 0 7.36 DDR 128

[edit] Features

Model Features
TwinView Dual-Display Architecture Digital Vibrance Control (DVC) Second Generation Transform and Lighting (T&L) NVIDIA Shading Rasterizer (NSR) High-Definition Video Processor (HDVP)
GeForce2 MX200 Yes Yes Yes Yes Yes
GeForce2 MX Yes Yes Yes Yes Yes
GeForce2 MX400 Yes Yes Yes Yes Yes
GeForce2 GTS Yes No Yes Yes Yes
GeForce2 Pro Yes No Yes Yes Yes
GeForce2 Ti Yes No Yes Yes Yes
GeForce2 Ultra Yes No Yes Yes Yes

[edit] GeForce3 series

Main article: GeForce 3 Series
  • All models are manufactured with a 150 nm manufacturing process
  • All models support DirectX 8.0 and OpenGL 1.3
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce3 Ti200 October 1, 2001 NV20 AGP 4x, PCI 64 175 400 4:1:8:4 700 700 1400 42.75 6.4 DDR 128
GeForce3 February 27, 2001 NV20 AGP 4x, PCI 64 200 460 4:1:8:4 800 800 1600 50 7.36 DDR 128
GeForce3 Ti500 October 1, 2001 NV20 AGP 4x, PCI 64, 128 240 500 4:1:8:4 960 960 1920 60 8 DDR 128

[edit] Features

Model Features
3D Textures Lightspeed Memory Architecture (LMA) nFiniteFX Engine Shadow Buffers
GeForce3 Ti200 Yes Yes Yes Yes
GeForce3 Yes Yes Yes Yes
GeForce3 Ti500 Yes Yes Yes Yes

[edit] GeForce4 series

Main article: GeForce 4 Series
  • All models are manufactured with a 150 nm manufacturing process
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support (version)
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce4 MX IGP + nForce2 October 1, 2002 N/A FSB Up to 128 system RAM 250 266-400 2:0:4:2 500 500 1000 0 2.128-6.4 DDR 64/128 7.0 1.2
GeForce4 MX420 February 6, 2002 NV17 AGP 4x 64 250 166 2:0:4:2 500 500 1000 0 2.656 SDR 64 7.0 1.2
GeForce4 MX440 SE 2002 NV17 AGP 4x 64, 128 250 332 2:0:4:2 500 500 1000 0 5.312 DDR 128 7.0 1.2
GeForce MX4000 December 14, 2003 NV18 AGP 8x 128 250 332 2:0:4:2 500 500 1000 0 2.656 DDR 64 7.0 1.2
GeForce PCX4300 February 19, 2004 NV18 PCI-E x16 128 250 666 2:0:4:2 500 500 1000 0 5.328 DDR 64 7.0 1.2
GeForce4 MX440 February 6, 2002 NV17 AGP 4x 64, 128 275 400 2:0:4:2 550 550 1100 0 6.4 DDR 128 7.0 1.2
GeForce4 MX440 8x September 25, 2002 NV18 AGP 8x 64, 128 275 500 2:0:4:2 550 550 1100 0 8 DDR 128 7.0 1.2
GeForce4 MX460 February 6, 2002 NV17 AGP 4x 64, 128 300 550 2:0:4:2 600 600 1200 0 8.8 DDR 128 7.0 1.2
GeForce4 Ti4200 April 16, 2002 NV25 AGP 4x 64, 128 250 444 (128 MB)
500 (64 MiB)		 4:2:8:4 1000 1000 2000 125 7.104 (128 MB)
8 (64 MB)		 DDR 64, 128 8.1 1.3
GeForce4 Ti4400 February 6, 2002 NV25 AGP 4x 128 275 550 4:2:8:4 1100 1100 2200 137.5 8.8 DDR 128 8.1 1.3
GeForce4 Ti4800 SE January 20, 2003 NV28 AGP 8x 128 275 550 4:2:8:4 1100 1100 2200 137.5 8.8 DDR 128 8.1 1.3
GeForce4 Ti4600 February 6, 2002 NV25 AGP 4x 128 300 650 4:2:8:4 1200 1200 2400 150 10.4 DDR 128 8.1 1.3
GeForce4 Ti4800 January 20, 2003 NV28 AGP 8x 128 300 640 4:2:8:4 1200 1200 2400 150 10.4 DDR 128 8.1 1.3
Model Features
Accuview Antialiasing (AA) Lightspeed Memory Architecture II (LMA II) nFiniteFX II Engine nView Video Processing Engine (VPE)
GeForce4 MX420 Yes Yes No Yes Yes
GeForce4 MX440 SE Yes Yes No Yes Yes
GeForce4 MX4000 Yes Yes No Yes Yes
GeForce4 PCX4300 Yes Yes No Yes Yes
GeForce4 MX440 Yes Yes No Yes Yes
GeForce4 MX440 8X Yes Yes No Yes Yes
GeForce4 MX460 Yes Yes No Yes Yes
GeForce4 Ti4200 Yes Yes Yes Yes No
GeForce4 Ti4400 Yes Yes Yes Yes No
GeForce4 Ti4600 Yes Yes Yes Yes No
GeForce4 Ti4800 Yes Yes Yes Yes No

[edit] GeForce FX (5xxx) series

Main article: GeForce FX Series
  • All models support DirectX 9.0b and OpenGL 1.5 (2.1 (software) with latest drivers)
  • The GeForce FX series runs vertex shaders in an array
Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce FX 5200 March 2003 NV34 150 AGP 8X, PCI 64, 128 250 400 4:1:4:4 1000 1000 1000 62.5 6.4 DDR 128
GeForce FX 5200 Ultra March 6, 2003 NV34 150 AGP 8X 64, 128 325 650 4:1:4:4 1300 1300 1300 81.25 10.4 DDR 128
GeForce PCX 5300 March 17, 2003 NV34 150 PCI-E x16 128 250 400 4:1:4:4 1000 1000 1000 62.5 6.4 DDR 128
GeForce FX 5500 March 2004 NV34B 150 AGP 8X, PCI 64, 128 270 400 4:1:4:4 1080 1080 1080 67.5 6.4 DDR 128
GeForce FX 5600 XT March 2003 NV31 130 AGP 8X 64, 128 235 400 4:1:4:4 940 940 940 58.75 6.4 DDR 128
GeForce FX 5600 March 2003 NV31 130 AGP 8X, PCI 64, 128 325 550 4:1:4:4 1300 1300 1300 81.25 8.8 DDR 128
GeForce FX 5600 Ultra March 6, 2003 NV31 130 AGP 8X 64, 128 350 700 4:1:4:4 1400 1400 1400 87.5 11.2 DDR 128
GeForce FX 5700 VE March 2004 NV36 130 AGP 8X 128, 256 235 400 4:3:4:4 940 940 940 106.5 6.4 DDR 128
GeForce FX 5700 LE March 2004 NV36 130 AGP 8X 128, 256 250 400 4:3:4:4 1000 1000 1000 187.5 6.4 DDR 128
GeForce FX 5700 2003 NV36 130 AGP 8X 128, 256 425 500 4:3:4:4 1700 1700 1700 318.75 8 DDR 128
GeForce PCX 5750 March 17, 2003 NV36 130 PCI-Ex16 128 425 500 4:3:4:4 1700 1700 1700 318.75 8 DDR 128
GeForce FX 5700 Ultra October 23, 2003 NV36 130 AGP 8X 128, 256 475 900 4:3:4:4 1900 1900 1900 356.25 14.4 DDR2 128
GeForce FX 5700 Ultra GDDR3 March 15, 2004 NV36 130 AGP 8X 128, 256 475 950 4:3:4:4 1900 1900 1900 356.25 15.2 GDDR3 128
GeForce FX 5800 January 27, 2003 NV30 130 AGP 8X 128 400 800 4:2:8:4 1600 1600 3200 200 12.8 DDR2 128
GeForce FX 5800 Ultra January 27, 2003 NV30 130 AGP 8X 128 500 1000 4:2:8:4 2000 2000 4000 250 16 DDR2 128
GeForce FX 5900 ZT December 15, 2003 NV35 130 AGP 8X 128 325 700 4:3:8:4 1300 1300 2600 343.75 22.4 DDR 256
GeForce FX 5900 XT 2003 NV35 130 AGP 8X 128 400 700 4:3:8:4 1600 1600 3200 300 22.4 DDR 256
GeForce FX 5900 May 2003 NV35 130 AGP 8X 128 400 850 4:3:8:4 1600 1600 3200 300 27.2 DDR 256
GeForce FX 5900 Ultra May 12, 2003 NV35 130 AGP 8X 128, 256 450 850 4:3:8:4 1800 1800 3600 337.5 27.2 DDR 256
GeForce PCX 5900 March 17, 2003 NV35 130 PCI-E x16 128, 256 450 850 4:3:8:4 1800 1800 3600 337.5 27.2 DDR 256
GeForce FX 5950 Ultra October 23, 2003 NV38 130 AGP 8X 256 475 950 4:3:8:4 1900 1900 3800 356.25 30.4 DDR 256
GeForce PCX 5950 February 17, 2004 NV38 130 PCI-E x16 256 475 950 4:3:8:4 1900 1900 3800 356.25 30.4 GDDR3 256

[edit] GeForce 6 (6xxx) series

Main article: GeForce 6 Series
Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce 6100 + nForce 410/430 October 20, 2005 MCP51 90 HyperTransport Up to 256 system RAM 425 200-400 (DDR)
400-1066 (DDR2)		 2:1:2:1 850 425 850 106.25 1.6-6.4 (DDR)
3.2-17.056 (DDR2)		 DDR, DDR2 64/128
GeForce 6150 SE + nForce 430 June 2006 MCP61 90 HyperTransport Up to 256 system RAM 425 400-800 2:1:2:1 850 425 850 106.25 3.2-16 DDR2 64/128
GeForce 6150 LE + nForce 430 June 2006 MCP61 90 HyperTransport Up to 256 system RAM 425 200-400 (DDR)
400-1066 (DDR2)		 2:1:2:1 850 425 850 106.25 1.6-6.4 (DDR)
3.2-17.056 (DDR2)		 DDR, DDR2 64/128
GeForce 6150 + nForce 430 October 20, 2005 MCP51 90 HyperTransport Up to 256 system RAM 475 200-400 (DDR)
400-1066 (DDR2)		 2:1:2:1 950 475 950 118.75 1.6-6.4 (DDR)
3.2-17.056 (DDR2)		 DDR, DDR2 64/128
GeForce 6200 LE 2005 NV44 110 AGP 8x, PCI-E x16 128, 256 350 532 2:1:2:2 700 700 700 87.5 4.256 DDR 64
GeForce 6200A April 4, 2005 NV44A 110 AGP 8x 128 350 500 4:2:4:4 1400 1400 1400 175 4 DDR 64
GeForce 6200 October 12, 2004 (PCI-E)
January 17, 2005 (AGP)		 NV43 110 AGP 8x, PCI, PCI-E x16 128, 256 300 550 4:3:4:2 1200 600 1200 225 8.8 DDR2 128
GeForce 6200 TurboCache December 15, 2004 NV44 110 PCI-E x16 128, 256 onboard + 16/32/64/128 System RAM 350 700 4:3:4:2 1400 700 1400 262.5 5.6 DDR 64
GeForce 6500 October 1, 2005 NV44 110 PCI-E x16 128, 256 400 666 4:3:4:2 1600 800 1600 300 5.328 DDR 128
GeForce 6600 LE 2005 NV43 110 AGP 8x, PCI-E x16 128, 256 300 400 4:3:4:4 1200 600 1200 225 6.4 DDR 128
GeForce 6600 August 12, 2004 NV43 110 AGP 8x, PCI-E x16 128, 256 300 550 8:3:8:4 2400 1200 2400 225 8.8 DDR 128
GeForce 6600 GT August 12, 2004 (PCI-E)
November 14, 2004 (AGP)		 NV43 110 AGP 8x, PCI-E x16 128, 256 500 950 (AGP)
1000 (PCI-E)		 8:3:8:4 4000 2000 4000 375 14.4 (AGP)
16 (PCI-E)		 GDDR3 128
GeForce 6800 LE July 22, 2004 (AGP)
January 16, 2005 (PCI-E)		 NV40 (AGP)
NV41 (PCI-E)		 130 AGP 8x, PCI-E x16 128 320 (AGP)
325 (PCI-E)		 700 8:4:8:8 2560 (AGP)
2600 (PCI-E)		 2560 (AGP)
2600 (PCI-E)		 2560 (AGP)
2600 (PCI-E)		 320 (AGP)
325 (PCI-E)		 22.4 DDR 256
GeForce 6800 XT September 30, 2005 NV40 (AGP)
NV41 (PCI-E)		 130 AGP 8x, PCI-E x16 256 325 700 8:4:8:8 2600 2600 2600 325 22.4 DDR 256
GeForce 6800 April 14, 2004 (AGP)
November 8, 2004 (PCI-E)		 NV40 (AGP)
NV41 (PCI-E)		 130 AGP 8x, PCI-E x16 128, 256 325 700 12:5:12:12 3900 3900 3900 406.25 22.4 DDR 256
GeForce 6800 GTO April 14, 2004 NV45 130 PCI-E x16 256 350 900 12:5:12:12 4200 4200 4200 437.5 28.8 GDDR3 256
GeForce 6800 GS November 7, 2005 (PCI-E)
December 8, 2005 (AGP)		 NV40 (AGP)
NV42 (PCI-E)		 130 PCI-E x16 128, 256 425 1000 12:5:12:12 5100 5100 5100 531.25 32 GDDR3 256
GeForce 6800 GT May 4, 2004 (AGP)
June 28, 2004 (PCI-E)		 NV40 (AGP)
NV45 (PCI-E)		 130 AGP 8x, PCI-E x16 128, 256 350 1000 16:6:16:16 5600 5600 5600 525 32 GDDR3 256
GeForce 6800 Ultra May 4, 2004 (AGP)
June 28, 2004 (PCI-E)
March 14, 2005 (512 MiB)		 NV40 (AGP)
NV45 (PCI-E)		 130 AGP 8x, PCI-E x16 256, 512 400 1050 (512 MiB)
1100 (256 MiB)		 16:6:16:16 6400 6400 6400 600 33.6 (512 MiB)
35.2 (256 MiB)		 GDDR3 256
GeForce 6800 Ultra Extreme May 4, 2004 NV40 130 AGP 8x 256 450 1100 16:6:16:16 7200 7200 7200 675 35.2 GDDR3 256


[edit] Features

Model Features
Transparency AA

(FW 91.47+)

 OpenEXR HDR Scalable Link Interface (SLI) TurboCache PureVideo w/WMV9 Decode PureVideo w/o WMV9 Decode
GeForce 6100 Yes No No No Limited No
GeForce 6150 SE Yes No No Driver-Side Only Limited No
GeForce 6150 Yes No No No Yes No
GeForce 6150 LE Yes No No Driver-Side Only Yes No
GeForce 6200 Yes No No Yes (PCI-E only) Yes No
GeForce 6500 Yes No Yes Yes Yes No
GeForce 6600 LE Yes Yes Yes (No SLI Connector) No Yes No
GeForce 6600 Yes Yes Yes (SLI Connector or PCI-E Interface) No Yes No
GeForce 6600 DDR2 Yes Yes Yes (SLI Connector or PCI-E Interface) No Yes No
GeForce 6600 GT Yes Yes Yes No Yes No
GeForce 6800 LE Yes Yes No No No Yes
GeForce 6800 XT Yes Yes Yes (PCI-E only) No Yes (NV42 only) No
GeForce 6800 Yes Yes Yes (PCI-E only) No Yes (NV41, NV42 only) No
GeForce 6800 GTO Yes Yes Yes No No Yes
GeForce 6800 GS Yes Yes Yes (PCI-E only) No Yes (NV42 only) Yes (NV40 only)
GeForce 6800 GT Yes Yes Yes (PCI-E only) No No Yes
GeForce 6800 Ultra Yes Yes Yes (PCI-E only) No No Yes

[edit] GeForce 7 (7xxx) series

Main article: GeForce 7 Series
Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce 7025 + nForce 630a July 2007 MCP68S 110 HyperTransport Up to 256 system RAM 425 533-800 2:1:2:2 850 850 850 106.25 8.528-12.8 DDR2 128
GeForce 7050PV + nForce 630a July 2007 MCP68V 110 HyperTransport Up to 256 system RAM 425 533-800 2:1:2:2 850 850 850 106.25 8.528-12.8 DDR2 128
GeForce 7050 + nForce 610i/630i July 2007 MCP76 90 FSB Up to 256 system RAM 500 667 2:1:2:2 1000 1000 1000 125 5.336 DDR2 64
GeForce 7100 + nForce 630i July 2007 MCP76 90 FSB Up to 256 system RAM 600 800 2:1:2:2 1200 1200 1200 150 6.4 DDR2 64
GeForce 7150 + nForce 630i July 2007 MCP76 90 FSB Up to 256 system RAM 630 800 2:1:2:2 1260 1260 1260 157.5 6.4 DDR2 64
GeForce 7100 GS August 8, 2006 NV44 110 PCI-E x16 128, 256 350 600 4:3:4:2 1400 700 1400 262.5 4.8 DDR2 64
GeForce 7200 GS January 18, 2006 G72 90 AGP 8x, PCI-E x16 128, 256 450 800 4:3:4:2 1800 900 1800 337.5 6.4 DDR2 64
GeForce 7300 SE March 22, 2006 G72 90 PCI-E x16 128 350 666 4:3:4:2 1800 900 1800 337.5 5.328 DDR2 64
GeForce 7300 LE March 22, 2006 G72 90 PCI-E x16 128 350 666 8:5:8:4 1800 900 1800 337.5 5.328 DDR2 64
GeForce 7300 GS January 18, 2006 G72 90 AGP 8x, PCI-E x16 128, 256 550 800 4:3:4:2 2200 1100 2200 412.5 6.4 DDR2 64
GeForce 7300 GT May 15, 2006 G73 90 AGP 8x, PCI-E x16 128, 256 350 650 8:5:8:4 2800 1400 2800 437.5 10.4 DDR2 128
GeForce 7600 GS March 22, 2006 (PCI-E)
July 1, 2006 (AGP)		 G73 90 AGP 8x, PCI-E x16 256 400 800 12:5:12:8 4800 3200 4800 500 12.8 DDR2 128
GeForce 7600 GT March 9, 2006 (PCI-E)
July 15, 2006 (AGP)		 G73 90 AGP 8x, PCI-E x16 256 560 1400 12:5:12:8 6720 4480 6720 700 22.4 GDDR3 128
GeForce 7600 GT 80 nm January 8, 2007 G73-B1 80 AGP 8x, PCI-E x16 256 560 1400 12:5:12:8 6720 4480 6720 700 22.4 GDDR3 128
GeForce 7800 GS February 2, 2006 G70 110 AGP 8x 256 375 1200 16:8:16:8 6000 3000 6000 562.5 38.4 GDDR3 256
GeForce 7800 GT August 11, 2005 G70 110 PCI-E x16 256 400 1000 20:7:20:16 8000 6400 8000 700 32 GDDR3 256
GeForce 7800 GTX June 22, 2005 (256 MB)
November 14, 2005 (512 MB)		 G70 110 PCI-E x16 256, 512 430 (256 MB)
550 (512 MB)		 1200 (256 MB)
1700 (512 MB)		 24:8:24:16 10320 (256 MB)
13200 (512 MB)		 6880 (256 MB)
8800 (512 MB)		 10320 (256 MB)
13200 (512 MB)		 860 (256 MB)
1100 (512 MB)		 38.4 (256 MB)
54.4 (512 MB)		 GDDR3 256
GeForce 7900 GS May 2006 (PCI-E)
April 2, 2007 (AGP)		 G71 90 AGP 8x, PCI-E x16 256 450 1320 20:7:20:16 9000 7200 9000 787.5 42.24 GDDR3 256
GeForce 7900 GT March 9, 2006 G71 90 PCI-E x16 512 450 1320 24:8:24:16 10800 7200 10800 900 42.24 GDDR3 256
GeForce 7900 GTO October 1, 2006 G71 90 PCI-E x16 512 650 1320 24:8:24:16 15600 10400 15600 1300 42.24 GDDR3 256
GeForce 7900 GTX March 9, 2006 G71 90 PCI-E x16 512 650 1600 24:8:24:16 15600 10400 15600 1300 51.2 GDDR3 256
GeForce 7900 GX2 March 9, 2006 G71 x2 90 PCI-E x16 1024 500 1200 24:8:24:16 x2 32000 24000 32000 2000 76.8 GDDR3 512
GeForce 7950 GT September 6, 2006 (PCI-E)
April 2, 2007 (AGP)		 G71 90 AGP 8x, PCI-E x16 512 550 1400 24:8:24:16 13200 8800 13200 1100 44.8 GDDR3 256
GeForce 7950 GX2 June 5, 2006 G71 x2 90 PCI-E x16 1024 500 1200 24:8:24:16 x2 32000 24000 32000 2000 76.8 GDDR3 512

[edit] Features

Model Features
Transparency AntiAliasing Gamma Correct AntiAliasing 64Bit OpenEXR HDR Scalable Link Interface (SLI) TurboCache Technology Dual Link DVI
GeForce 7100 GS Yes No No No Yes No
GeForce 7200 GS Yes Yes Yes No Yes No
GeForce 7300 SE Yes Yes Yes No Yes No
GeForce 7300 LE Yes Yes Yes No Yes No
GeForce 7300 GS Yes Yes Yes Yes (PCI-E only)
(No SLI bridge)		 Yes No
GeForce 7300 GT Yes Yes Yes Yes (PCI-E only)
(No SLI bridge)		 No One port
GeForce 7600 GS Yes Yes Yes Yes (PCI-E only) No One port
GeForce 7600 GT Yes Yes Yes Yes (PCI-E only) No One port
GeForce 7600 GT (80 nm) Yes Yes Yes Yes No One port
GeForce 7650 GS (80 nm) Yes Yes Yes Yes (Depending on OEM Design) No One port
GeForce 7800 GS Yes Yes Yes No No One port
GeForce 7800 GT Yes Yes Yes Yes No One port
GeForce 7800 GTX Yes Yes Yes Yes No One port
GeForce 7800 GTX 512 Yes Yes Yes Yes No One port
GeForce 7900 GS Yes Yes Yes Yes (PCI-E only) No Two ports
GeForce 7900 GT Yes Yes Yes Yes No Two ports
GeForce 7900 GTO Yes Yes Yes Yes No Two ports
GeForce 7900 GTX Yes Yes Yes Yes No Two ports
GeForce 7950 GT Yes Yes Yes Yes (PCI-E only) No Two ports
GeForce 7950 GX2 Yes Yes Yes Yes No Two ports

[edit] GeForce 8 (8xxx) series

Main article: GeForce 8 Series
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MiB) Config core1 Clock rate Fillrate Memory API support (version) Processing Power (GFLOPs) TDP (watts) GFLOPS/ watt Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 8100 mGPU[8] 2008 MCP78 80 Unknown Unknown PCIe 2.0 x16 Up to 512 from system memory 8:8:4 500 1200 800
(system memory)		 2 4 6.4/12.8 DDR2 64/128 10.0 3.3 28.8 Unknown Unknown The block of decoding of HD-video PureVideo HD is disconnected
GeForce 8200 mGPU[8] 2008 MCP78 80 Unknown Unknown PCIe 2.0 x16 Up to 512 from system memory 8:8:4 500 1200 800
(system memory)		 2 4 6.4/12.8 DDR2 64/128 10.0 3.3 28.8 Unknown Unknown PureVideo 3 with VP3
GeForce 8300 mGPU[8] 2008 MCP78 80 Unknown Unknown PCIe 2.0 x16 Up to 512 from system memory 8:8:4 500 1500 800
(system memory)		 2 4 6.4/12.8 DDR2 64/128 10.0 3.3 36 Unknown Unknown PureVideo 3 with VP3
GeForce 8300 GS[9] July 2007 G98 65 210 86 PCIe 2.0 x16 512 8:8:4 450 900 800 1.8 3.6 6.4 DDR2 64 10.0 3.3 22 40 0.55 OEM only
GeForce 8400 GS June 15, 2007 G86 80 210 127 PCIe 1.0 x16, PCI 128, 256, 512 16:8:4 450 900 800 1.8 3.6 6.4 DDR2 64 10.0 3.3 43 40 1.08
GeForce 8400 GS rev.2 December 4, 2007 G98 65 Unknown 86 PCIe 2.0 x16, PCI 128, 256, 512 8:8:4 567 1400 800 2.268 4.536 6.4 DDR2 64 10.0 3.3 33 25 1.32
GeForce 8500 GT April 17, 2007 G86 80 210 127 PCIe 1.0 x16, PCI 256, 512, 1024 16:8:8 450 900 800 3.6 3.6 12.8 DDR2 128 10.0 3.3 43 45 0.96
GeForce 8600 GS April 2007 G84 80 289 169 PCIe 1.0 x16 256, 512 32:16:8 540 1180 800 4.32 8.64 12.8 DDR2 128 10.0 3.3 113 47 2.40 OEM only
GeForce 8600 GT April 17, 2007 G84 80 289 169 PCIe 1.0 x16, PCI 256, 512, 1024 32:16:8 540 1180 800
1400		 4.32 8.64 12.8
22.4		 DDR2
GDDR3		 128 10.0 3.3 113 47 2.40
GeForce 8600 GTS April 17, 2007 G84 80 289 169 PCIe 1.0 x16 256, 512 32:16:8 675 1450 2000 5.4 10.8 32 GDDR3 128 10.0 3.3 139 75 1.85
GeForce 8800 GS Jan 2008 G92 65 754 324 PCIe 2.0 x16 384, 768 96:48:12 550 1375 1600 6.6 26.4 38.4 GDDR3 192 10.0 3.3 396 105 3.77
GeForce 8800 GTS (G80) February 12, 2007 (320)
November 8, 2006 (640)		 G80 90 681 484 PCIe 1.0 x16 320, 640 96:242:20 513 1188 1584 10.26 12.312 63.4 GDDR3 320 10.0 3.3 346 143 2.42
GeForce 8800 GTS 112 (G80) November 19, 2007 G80 90 681 484 PCIe 1.0 x16 640 112:282:20 513 1188 1584 10.26 14.364 63.4 GDDR3 320 10.0 3.3 399 150 2.66 only XFX, EVGA and BFG models, very short-lived[10]
GeForce 8800 GT October 29, 2007 (512)
December 11, 2007 (256, 1024)		 G92 65 754 324 PCIe 2.0 x16 256, 512, 1024 112:56:16 600 1500 1400 (256)
1800 (512, 1024)		 9.6 33.6 57.6 GDDR3 256 10.0 3.3 504 125 4.03
GeForce 8800 GTS (G92) December 11, 2007 G92 65 754 324 PCIe 2.0 x16 512 128:64:16 650 1625 1940 10.4 41.6 62.1 GDDR3 256 10.0 3.3 624 135 4.62
GeForce 8800 GTX November 8, 2006 G80 90 681 484 PCIe 1.0 x16 768 128:322:24 575 1350 1800 13.8 18.4 86.4 GDDR3 384 10.0 3.3 518 155 3.34
GeForce 8800 Ultra May 2, 2007 G80 90 681 484 PCIe 1.0 x16 768 128:322:24 612 1500 2160 14.688 19.584 103.7 GDDR3 384 10.0 3.3 576 171 3.37
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory min (MB) Config core1 Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL Processing Power (GFLOPs) TDP (Watts) GFLOPS/ watt Comments
Clock rate Fillrate Memory API support (version)

[edit] Features

  • Compute Capability: 1.1 has support for Atomic functions, which are used to write thread-safe programs.
Model Features
Coverage
Sample
Anti-Aliasing		 Angle
Independent
Anisotropic
Filtering		 128Bit
OpenEXR
HDR		 Scalable
Link
Interface
(SLI)		 3-Way
SLI		 PureVideo HD
with VP1		 PureVideo 2 with VP2,

BSP Engine, and AES128 Engine

 PureVideo 3 with VP3,

BSP Engine, and AES128 Engine

 Compute
Capability
1.1
GeForce 8300 GS (G86) Yes Yes Yes No No No Yes No 1.1
GeForce 8400 GS (G98) Yes Yes Yes No No No No Yes 1.1
GeForce 8400 GS (G86) Yes Yes Yes No No No Yes No 1.1
GeForce 8500 GT Yes Yes Yes Yes (No SLI Bridge) No No Yes No 1.1
GeForce 8600 GT Yes Yes Yes Yes No No Yes No 1.1
GeForce 8600 GTS Yes Yes Yes Yes No No Yes No 1.1
GeForce 8800 GS (G92) Yes Yes Yes Yes No No Yes No 1.1
GeForce 8800 GTS (G80) Yes Yes Yes Yes No Yes No No 1.0
GeForce 8800 GTS Rev. 2 (G80) Yes Yes Yes Yes No Yes No No 1.0
GeForce 8800 GT (G92) Yes Yes Yes Yes No No Yes No 1.1
GeForce 8800 GTS (G92) Yes Yes Yes Yes No No Yes No 1.1
GeForce 8800 GTX Yes Yes Yes Yes Yes Yes No No 1.0
GeForce 8800 Ultra Yes Yes Yes Yes Yes Yes No No 1.0

[edit] GeForce 9 (9xxx) series

Main article: GeForce 9 Series
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core[1] Clock rate Fillrate Memory API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 9300 mGPU October 2008 MCP7A-S 65 282 162 1 PCIe 2.0 x16 Up to 512 from system memory 16:8:4 450 1200 800
1333		 1.8 3.6 6.4/12.8
10.664/21.328		 DDR2
DDR3		 64/128 10.0 3.3 57.6 Unknown Unknown based on 8400 GS
GeForce 9400 mGPU October 2008 MCP7A-U 65 282 162 1 PCIe 2.0 x16 Up to 512 from system memory 16:8:4 580 1400 800
1333		 2.32 4.64 6.4/12.8
10.664/21.328		 DDR2
DDR3		 64/128 10.0 3.3 67.2 12 5.6 based on 8400 GS
GeForce 9300 GE[11] June 2008 G98 65 Unknown 86 1 PCIe 2.0 x16 256 8:8:4 540 1300 1000 2.16 4.32 8 DDR2 64 10.0 3.3 31.2  ?? Unknown
GeForce 9300 GS[11] June 2008 G98 65 Unknown 86 1 PCIe 2.0 x16 256 8:8:4 567 1400 1000 2.268 4.536 8 DDR2 64 10.0 3.3 33.6  ?? Unknown
GeForce 9400 GT August 27, 2008 G96a/b 65/55 314 144 1 PCIe 2.0 x16, PCI 256, 512, 1024 16:8:4 550 1400 800
1600		 2.2 4.4 12.8
25.6		 GDDR2
GDDR3		 128 10.0 3.3 67.2 50 1.34
GeForce 9500 GT July 29, 2008 G96a/b 65/55 314 144 1 PCIe 2.0 x16, PCI 256, 512, 1024 32:16:8 550 1400 1000
1600		 4.4 8.8 16.0
25.6		 DDR2
GDDR3		 128 10.0 3.3 134.4 50 2.69
GeForce 9600 GSO May 2008 G92 65 754 324 1 PCIe 2.0 x16 384, 768, 1536 96:48:12 550 1375 1600 6.6 26.4 38.4 GDDR3 192 10.0 3.3 396 84 4,71
GeForce 9600 GSO 512 October 2008 G94a/b 65/55 505 240/196? 1 PCIe 2.0 x16 512 48:24:16 650 1625 1800 10.4 15.6 57.6 GDDR3 256 10.0 3.3 234 90 2.6
GeForce 9600 GT Green Edition 2009 G94b 55 505 196? 1 PCIe 2.0 x16 512, 1024 64:32:16 600
625		 1500
1625		 1400/1800
1800		 9.6
10		 19.2
20		 44.8/57.6
57.6		 GDDR3 256 10.0 3.3 288
312		 59 4.88
5.29		 Core Voltage - 1 volt
GeForce 9600 GT February 21, 2008 G94a/b 65/55 505 240/196? 1 PCIe 2.0 x16 512, 1024 64:32:16 650 1625 1800 10.4 20.8 57.6 GDDR3 256 10.0 3.3 312 95 3.28
GeForce 9800 GT Green Edition 2009 G92b 55 754 260 1 PCIe 2.0 x16 512, 1024 112:56:16 550 1375 1400
1600
1800		 8.8 30.8 44.8
51.2
57.6		 GDDR3 256 10.0 3.3 462 75 6.16 Core Voltage - 1 volt
GeForce 9800 GT July 2008 G92a/b 65/55 754 324/260 1 PCIe 2.0 x16 512, 1024 112:56:16 600 1500 1800 9.6 33.6 57.6 GDDR3 256 10.0 3.3 504 125/105 4.03/4.8
GeForce 9800 GTX April 1, 2008 G92 65 754 324 1 PCIe 2.0 x16 512 128:64:16 675 1688 2200 10.8 43.2 70.4 GDDR3 256 10.0 3.3 648 140 4.63
GeForce 9800 GTX+ July 16, 2008 G92b 55 754 260 1 PCIe 2.0 x16 512, 1024 128:64:16 738 1836 2200 11.808 47.232 70.4 GDDR3 256 10.0 3.3 705 141 5.0
GeForce 9800 GX2 March 18, 2008 G92 65 2x 754 2x 324 2 PCIe 2.0 x16 2x 512 2x 128:64:16 600 1500 2000 2x 9.6 2x 38.4 2x 64.0 GDDR3 2x 256 10.0 3.3 2x 576 197 5.85
Model Launch Codename Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core[1] Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL Processing Power GFLOPs TDP (watts) GFLOPS/ watt Comments

[edit] Features

  • Compute Capability: 1.1 has support for Atomic functions, which are used to write thread-safe programs.
Model Features
Scalable Link Interface (SLI) Coverage Sample
AA		 Angle Independent
AF		 128 bit OpenEXR PureVideo 2 with VP2,

BSP Engine, and AES128 Engine

 PureVideo 3 with VP3,

BSP Engine, and AES128 Engine
GeForce 9300 GE (G98) Yes Yes No Yes
GeForce 9300 GS (G98)
GeForce 9400 GT Yes No
GeForce 9500 GT
GeForce 9600 GSO
GeForce 9600 GT
GeForce 9800 GT
GeForce 9800 GTX Yes
3-way (link 3 GTXs)
GeForce 9800 GTX+
GeForce 9800 GX2 Yes
Quad (link 2 GX2s)

[edit] GeForce 100 Series

Model Launch Code name Fab Process (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core 1 Clock rate Fillrate Memory Configuration API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL
GeForce G 100 March 10, 2009 G98 65 Unknown 86 1 PCIe 2.0 x16 512 8:8:4 567 1400 500 2.15 4.3 8.0 DDR2 64 10.0 3.3 33.6 35 0.96 OEM products
GeForce GT 120 March 10, 2009 G96b 55 314 121 1 PCIe 2.0 x16 512 32:16:8 500 1400 800 4.4 8.8 16.0 DDR2 128 10.0 3.3 134.4 50 2.69 OEM products
GeForce GT 130 March 10, 2009 G94b 55 505 196? 1 PCIe 2.0 x16 1536 48:24:12 500 1250 500 6 12 24.0 DDR2 192 10.0 3.3 180 75 2.4 OEM products
GeForce GT 140 March 10, 2009 G94b 55 505 196? 1 PCIe 2.0 x16 512

1024

 64:32:16 650 1625 1800 10.4 20.8 57.6 GDDR3 256 10.0 3.3 312 105 2.97 OEM products
GeForce GTS 150 March 10, 2009 G92b 55 754 260 1 PCIe 2.0 x16 1024 128:64:16 738 1836 1000 11.808 47.232 64.0 GDDR3 256 10.0 3.3 705 141 5.0 OEM products

[edit] GeForce 200 Series

Main article: GeForce 200 Series
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core 1 Clock rate Fillrate Memory Configuration API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL
GeForce 205 November 26, 2009 GT218 40 260 57 1 PCIe 2.0 x16 512 8:4:4 589 1402 1000 2.356 2.356 8 DDR2 64 10.1 3.3 33.4 30.5 1.06 OEM only
GeForce 210 October 12, 2009 GT218 40 260 57 1 PCIe 2.0 x16, PCI 512 16:8:4 589 1402 1000
1600		 2.356 4.712 8
12.8		 DDR2
DDR3		 64 10.1 3.3 67.296 30.5 2.21
GeForce GT 220 October 12, 2009 GT216 40 486 100 1 PCIe 2.0 x16 512
1024		 48:16:8 615(OEM)
625		 1335(OEM)
1360		 1000
1580		 5 10 16
25.3		 DDR2
DDR3		 128 10.1 3.3 192(OEM)
196		 58 3.31(OEM)
3.38
GeForce GT 230 v.1 2009 G94b 55 505 196? 1 PCIe 2.0 x16 512
1024		 48:24:16 650 1625 1800 10.4 15.6 57.6 GDDR3 256 10 3.3 234 75 3.12 OEM only
GeForce GT 230 v.2 2009 G92b 55 754 260 1 PCIe 2.0 x16 1536 96:48:12 500 1242 1000 6 24 24 DDR2 192 10 3.3 357.69 75 4.77 OEM only
GeForce GT 240 November 17, 2009 GT215 40 727 139 1 PCIe 2.0 x16 512
1024		 96:32:8 550 1340 1800
2000
3400(GDDR5)		 4.4 17.6 28.8(OEM)
32
54.4(GDDR5)		 DDR3
GDDR3
GDDR5		 128 10.1 3.3 385.9 69 5.59
GeForce GTS 240 Q4 2009 G92a/b 65/55 754 324/260 1 PCIe 2.0 x16 1024 112:56:16 675 1620 1100 10.8 37.8 70.4 GDDR3 256 10.0 3.3 554.32 120 4.62 OEM only
GeForce GTS 250 March 3, 2009 G92b 55 754 260 1 PCIe 2.0 x16 512
1024		 128:64:16 738 1836 2200
2000		 11.808 47.232 70.4
64		 GDDR3 256 10.0 3.3 705.024 145 4.86 Some cards are rebranded GeForce 9800 GTX+
GeForce GTX 260 June 16, 2008 GT200 65 1400 576 1 PCIe 2.0 x16 896 192:64:28 576 1242 1998 16.128 36.864 111.9 GDDR3 448 10.0 3.3 715.392 202 3.54 Replaced by GTX 260 Core 216
GeForce GTX 260 Core 216 September 16, 2008 GT200a/b 65/55 1400 576/470 1 PCIe 2.0 x16 896 (1792) 216:72:28 576 1242 1998 16.128 41.472 111.9 GDDR3 448 10.0 3.3 804.816/874.8(55nm) 182/171 4.42/4.71
GeForce GTX 275 April 9, 2009 GT200b 55 1400 470 1 PCIe 2.0 x16 896 240:80:28 633 1404 2268 17.724 50.6 127.0 GDDR3 448 10.0 3.3 1010.880 219 4.62 Effectively one-half of the GTX 295
GeForce GTX 280 June 17, 2008 GT200 65 1400 576 1 PCIe 2.0 x16 1024 240:80:32 602 1296 2214 19.264 48.16 141.7 GDDR3 512 10.0 3.3 933.120 236 3.95 Replaced by GTX 285
GeForce GTX 285 January 15, 2009 GT200b 55 1400 470 1 PCIe 2.0 x16 1024 (2048*) 240:80:32 648 1476 2484 20.736 51.84 159.0 GDDR3 512 10.0 3.3 1062.720 204 5.24 Palit and EVGA launched 2GB versions. EVGA GTX285 Classified can support 4-way SLI
GeForce GTX 295 January 8, 2009 GT200b 55 2x 1400 2x 470 2 PCIe 2.0 x16 2x 896 2x 240:80:28 576 1242 1998 2x 16.128 2x 46.08 2x 111.9 GDDR3 2x 448 10.0 3.3 1788.480 289 6.19 Dual PCB models were phased out in favor of a single PCB model with 2 GPUs
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core 1 Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL GFLOPs (MADD+MUL) TDP (Watts) GFLOPS/ watt Comments
Clock rate Fillrate Memory Configuration API support (version)

[edit] Features

Compute Capability: 1.1 (G92 [GTS250] GPU)
Compute Capability: 1.2 (GT215, GT216, GT218 GPUs)
Compute Capability: 1.3 has double precision support for use in GPGPU applications. (GT200a/b GPUs only)

Model Features
Scalable Link Interface (SLI) Coverage Sample
AA		 Angle Independent
AF		 240 bit OpenEXR PureVideo 2 with VP2

Engine: (BSP and 240 AES)

 PureVideo 4 with VP4 Engine
GeForce 210 No Yes No Yes
GeForce GT 220
GeForce GT 240
GeForce GTS 250 Yes
3-Way (4-way for EVGA 285 Classified)		 Yes No
GeForce GTX 260
GeForce GTX 260 Core 216
GeForce GTX 260 Core 216 (55 nm)
GeForce GTX 275
GeForce GTX 280
GeForce GTX 285
GeForce GTX 295 Yes
Quad (link 2 295s)

[edit] GeForce 300 Series

Main article: GeForce 300 Series
  • 1 Unified Shaders (Vertex shader / Geometry shader / Pixel shader) : Texture mapping unit : Render Output unit
  • 2 Each Streaming Multiprocessor(SM) in the chip of G80/GT200 architecture contains 8 SPs and 2 SFUs. Each SP can fulfil up to two single precision operations MAD per clock. Each SFU can fulfil up to four operations SF per clock (these units can also handle single-precision floating-point multiplications per clock). The approximate ratio of operations MAD to operations SF is equal 2:1. The theoretical SP+SFU performance in single-precision floating point operations [FLOPSsp+sfu, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp+sfu ≈ f × n × 3. Alternative formula:FLOPSsp+sfu ≈ f × m × ( 8 SPs * 2 (MAD) + 4 * 2 SFUs ). [m] - SM count.[12][13]

SP - Shader Processor (Unified Shader, CUDA Core), SFU - Special Function Unit, SM - Streaming Multiprocessor, MAD - ADD+MUL.

Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) Config core 1 Clock rate Fillrate Memory Configuration API support (version) Processing Power GFLOPs2 TDP (watts) GFLOPS/ watt Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL
GeForce 310 November 27, 2009 GT218 40 260 57 1 PCIe 2.0 x16 512 16:8:4 589 1402 1000 2.356 4.712 8 DDR2 64 10.1 3.3 67.296 30.5 2.21 OEM Card
GeForce 315 February, 2010 GT216 40 486 100 1 PCIe 2.0 x16 512 48:16:8 475 1100 1580 3.8 7.6 12.6 DDR3 64 10.1 3.3 158.4 33 4.8 OEM Card
GeForce GT 320 February, 2010 GT215 40 727 144 1 PCIe 2.0 x16 1024 72:24:8 540 1302 1580 4.32 12.96 25.3 GDDR3 128 10.1 3.3 281.23 43 6.54 OEM Card
GeForce GT 330 February, 2010 G92b? 55? 754? 260? 1 PCIe 2.0 x16 1024
1536
2048		 96:48?:8?
96:48?:12?
112:56?:16?		 500-550 1250–1340 1000 (DDR2)
1600 (GDDR3)		 Unknown Unknown 24-32 DDR2
GDDR3		 128
192
256		 10 3.3 Unknown 75 Unknown OEM Card. Specifications vary depending on the OEM.
GeForce GT 340 February, 2010 GT215 40 727 144 1 PCIe 2.0 x16 512, 1024 96:32:8 550 1340 3400 4.4 17.6 54.4 GDDR5[14] 128 10.1 3.3 385.9 69 5.59 OEM Card

[edit] GeForce 400 Series

Main article: GeForce 400 Series

Please take note: Memory bandwidths mentioned in the following table refer nVidia reference designs. Actual bandwidth can be higher or lower depending on the manufacturer of the graphic board.

  • 1 SPs - Shader Processors - Unified Shaders (Vertex shader / Geometry shader / Pixel shader) : TMUs - Texture mapping units : Render Output unit
  • 2 Each Streaming Multiprocessor(SM) in the GPU of GF100 architecture contains 32 SPs and 4 SFUs. Each Streaming Multiprocessor(SM) in the GPU of GF104/106/108 architecture contains 48 SPs and 8 SFUs. Each SP can fulfil up to two single precision operations FMA per clock. Each SFU can fulfil up to four operations SF per clock. The approximate ratio of operations FMA to operations SF is equal: for GF100 4:1 and for GF104/106/108 3:1. The theoretical shader performance in single-precision floating point operations(FMA) [FLOPSsp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp ≈ f × n × 2. Alternative formula: for GF100 FLOPSsp ≈ f × m × (32 SPs × 2(FMA)) and for GF104/106/108 FLOPSsp ≈ f × m × (48 SPs × 2(FMA)). [m] - SM count. Total Processing Power: for GF100 FLOPSsp ≈ f × m ×(32 SPs × 2(FMA) + 4 × 4 SFUs) and for GF104/106/108 FLOPSsp ≈ f × m × (48 SPs × 2(FMA) + 4 × 8 SFUs) or for GF100 FLOPSsp ≈ f × n × 2.5 and for GF104/106/108 FLOPSsp ≈ f × n × 8 / 3.[15] where:

SP - Shader Processor (Unified Shader, CUDA Core), SFU - Special Function Unit, SM - Streaming Multiprocessor, FMA - Fused MUL+ADD.

  • 3 Each SM in the GF100 contains 4 texture filtering units for every texture address unit. The complete GF100 die contains 64 texture address units and 256 texture filtering units.[16] Each SM in the GF104/106/108 architecture contains 8 texture filtering units for every texture address unit but has doubled both addressing and filtering units. The complete GF104 die also contains 64 texture address units and 512 texture filtering units despite the halved SM count, the complete GF106 die contains 32 texture address units and 256 texture filtering units and the complete GF108 die contains 16 texture address units and 128 texture filtering units.[17]
  • 4 Note that while GTX 460's TDP is comparable to that of AMD's HD5000 series, GF100-based cards (GTX 480/470/465) are rated much lower, e.g. GTX 480 with 250W TDP consumes more power than HD 5970 with 297W TDP.[18]
  • 6 The 400 series is the only non-OEM family since GeForce 8 not to include an official dual-GPU solution. However, on March 18, 2011, EVGA released the first single-PCB card with dual 460's on board. The card came with 2048 MB of memory at 3600 MHz and 672 shader processors at 1400 MHz and was offered at the MSRP of $429.
  • 7 The GeForce 405 card is a remarked GeForce 310 which itself is a remarked GeForce 210.
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) SM count Config core 1,3 Clock rate Fillrate Memory Configuration API support (version) GFLOPs (FMA)2 TDP (watts)4 GFLOPS/ watt Release Price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL OpenCL5
GeForce 405 (OEM)7 Unknown GT218 40 260 57 1 PCIe 2.0 x16 512

1024

 1 16:8:4 589 1402 790 Unknown Unknown 12.6 DDR3 64 10.1 3.3 1.1 Unknown 30.5 Unknown OEM
GeForce GT 420 (OEM) September 3, 2010 GF108 40 585 116 1 PCIe 2.0 x16 2048 1 48:4:4 700 1400 1800 2.8 2.8 28.8 GDDR3 128 11 4.2 1.1 134.4 50 2.69 OEM
GeForce GT 430 (OEM) October 11, 2010 GF108 40 585 116 1 PCIe 2.0 x16 2048 2 96:16:4 700 1400 1600
1800		 2.8 5.6 25.6
28.8		 GDDR3 128 11 4.2 1.1 268.8 60 4.48 OEM
GeForce GT 430 October 11, 2010 GF108 40 585 116 1 PCIe 2.0 x16, PCI 512
1024		 2 96:16:4 700 1400 1800 2.8 5.6 28.8 GDDR3 128 11 4.2 1.1 268.8 49 5.49 $79
GeForce GT 440 February 1, 2011 GF108 40 585 116 1 PCIe 2.0 x16 512
1024
2048		 2 96:16:4 810 1620 1800
3200		 13.2 13.2 28.8
51.2		 GDDR3
GDDR5		 128 11 4.2 1.1 311.04 65 4.78 $79
GeForce GT 440 (OEM) October 11, 2010 GF106 40 1170 238 1 PCIe 2.0 x16 1536
3072		 3 144:24:24 594 1189 1800 14.26 14.26 43.2 GDDR3 192 11 4.2 1.1 342.43 56 6.11 OEM
GeForce GTS 450 (OEM) October 11, 2010 GF106 40 1170 238 1 PCIe 2.0 x16 1536 3 144:24:24 790 1580 4000 18.96 18.96 96 GDDR5 192 11 4.2 1.1 455.04 106 4.29 OEM
GeForce GTS 450 September 13, 2010/March 15, 2011 GF106/GF116-200 40 1170 238 1 PCIe 2.0 x16 512
1024		 4 192:32:16 783 1566 3608 12.53 25.06 57.73 GDDR5 128 11 4.2 1.1 601.34 106 5.67 $129
GeForce GTX 460 SE November 15, 2010 GF104 40 1950 332 1 PCIe 2.0 x16 1024 6 288:48:32 650 1300 3400 20.8 31.2 108.8 GDDR5 256 11 4.2 1.1 748.8 150 4.99 $160
GeForce GTX 460 (OEM) October 11, 2010 GF104 40 1950 332 1 PCIe 2.0 x16 1024 7 336:56:32 650 1300 3400 20.8 36.4 108.8 GDDR5 256 11 4.2 1.1 873.6 150 5.82 OEM
GeForce GTX 4606 July 12, 2010 GF104 40 1950 332 1 PCIe 2.0 x16 768 7 336:56:24 675 1350 3600 16.2 37.8 86.4 GDDR5 192 11 4.2 1.1 907.2 150 6.05 $199
1024
2048		 336:56:32 21.6 115.2 256 160 5.67 $229
GeForce GTX 460 v2 September 24, 2011 GF114 40 1950 332 1 PCIe 2.0 x16 1024 7 336:56:24 778 1556 4008 18.67 43.57 96.2 GDDR5 192 11 4.2 1.1 1045.6 160 6.54 $199
GeForce GTX 465 May 31, 2010 GF100 40 3000[19] 529 1 PCIe 2.0 x16 1024 11 352:44:32 607 1215 3206 19.42 26.71 102.6 GDDR5 256 11 4.2 1.1 855.36 2004 4.28 $279
GeForce GTX 470 March 26, 2010 GF100 40 3000 529 1 PCIe 2.0 x16 1280 14 448:56:40 607 1215 3348 24.28 34 133.9 GDDR5 320 11 4.2 1.1 1088.64 2154 5.06 $349
GeForce GTX 480 March 26, 2010 GF100 40 3000 529 1 PCIe 2.0 x16 1536 15 480:60:48 700 1401 3696 33.60 42 177.4 GDDR5 384 11 4.2 1.1 1344.96 2504 5.38 $499
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) SM count Config core 1,3 Clock rate Fillrate Memory Configuration API support (version) GFLOPs (FMA)2 TDP (watts)4 GFLOPS/ watt Release Price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL OpenCL

[edit] GeForce 500 Series

Main article: GeForce 500 Series
  • 1 SPs - Shader Processors - Unified Shaders (Vertex shader / Geometry shader / Pixel shader) : TMUs - Texture mapping units : Render Output unit
  • 2 Each Streaming Multiprocessor(SM) in the GPU of GF110 architecture contains 32 SPs and 4 SFUs. Each Streaming Multiprocessor(SM) in the GPU of GF114/116/118/119 architecture contains 48 SPs and 8 SFUs. Each SP can fulfil up to two single precision operations FMA per clock. Each SFU can fulfil up to four SF operations per clock. The approximate ratio of operations FMA to operations SF is equal 4:1. The theoretical shader performance in single-precision floating point operations(FMA)[FLOPSsp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp ≈ f × n × 2. Alternative formula: FLOPSsp ≈ f × m × (32 SPs × 2(FMA)). [m] - SM count. Total Processing Power: FLOPSsp ≈ f × m × (32 SPs × 2(FMA) + 4 × 4 SFUs) or FLOPSsp ≈ f × n × 2.5.
  • 3 Each SM in the GF110 contains 4 texture filtering units for every texture address unit. The complete GF110 die contains 64 texture address units and 256 texture filtering units.[20] Each SM in the GF114/116/118 architecture contains 8 texture filtering units for every texture address unit but has doubled both addressing and filtering units.
  • 4 Internally referred to as GF104B[21]
  • 5 Internally referred to as GF100B[22]
  • 6 Similar to previous generation, GTX 580 and most likely future GTX 570, while reflecting its improvement over GF100, still have lower rated TDP and higher power consumption, e.g. GTX580 (243W TDP) is slightly less power hungry than GTX 480 (250W TDP). This is managed by clock throttling through drivers when a dedicated power hungry application is identified that could breach card TDP. Application name changing will disable throttling and enable full power consumption, which in some cases could be close to that of GTX480.[23]
  • 7 Some companies have announced that they will be offering the GTX580 with 3GB VRAM.[24]
  • 9 1024 MB RAM on 192-bit bus assemble with 4 * (128 MB) + 2 * (256 MB).
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) SM count Config core 1,3 Clock rate Fillrate Memory Configuration API support (version) GFLOPs (FMA)2 TDP (watts)6 GFLOPS/ watt Release Price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL OpenCL8
GeForce 510 September 29, 2011 GF119 40 Unknown Unknown 1 PCIe 2.0 x16 1024

2048

 1 48:8:4 523 1046 1800 2.1 4.2 14.4 DDR3 64 11 4.2 1.1 100.4 25 4.02 OEM
GeForce GT 520 April 13, 2011 GF119 40 Unknown Unknown 1 PCIe 2.0 x16, PCI 1024

2048

 1 48:8:4 810 1620 1800 3.24 6.5 14.4 DDR3 64 11 4.2 1.1 155.5 29 5.36 $59
GeForce GT 530 May 14, 2011 GF108 (?) 40 ~585 ~116 1 PCIe 2.0 x16 1024

2048

 2 96:16:4 700 1400 1800 2.8 11.2 28.8 DDR3 128 11 4.2 1.1 268.8 50 5.38 OEM
GeForce GT 545 DDR3 May 14, 2011 GF116 40 ~1170 ~238 1 PCIe 2.0 x16 1536

3072

 3 144:24:16 720 1440 1800 14.26 14.26 43 DDR3 192 11 4.2 1.1 415.07 70 5.93 $149
GeForce GT 545 GDDR5 May 14, 2011 GF116 40 ~1170 ~238 1 PCIe 2.0 x16 1024 3 144:24:16 870 1740 1998 13.92 20.88 64 GDDR5 128 11 4.2 1.1 501.12 105 4.77 OEM
GeForce GTX 550 Ti March 15, 2011 GF116-400 40 ~1170 ~238 1 PCIe 2.0 x16 1024 4 192:32:24 900 1800 4104 21.6 28.8 98.5 GDDR5 192 9 11 4.2 1.1 691.2 116 5.96 $149
GeForce GTX 555 N/A GF1144 40 1950 ~332 1 PCIe 2.0 x16 1024 6 288:48:32 776 1553 3828 N/A 37.2 91.9 GDDR5 192 9 11 4.2 1.1 708.2 N/A N/A OEM
GeForce GTX 560 May 17, 2011 GF1144 40 1950 ~332 1 PCIe 2.0 x16 1024 7 336:56:32 810 1620 4004 25.9 45.3 128.1 GDDR5 256 11 4.2 1.1 1088.6 150 7.26 $199
GeForce GTX 560 Ti January 25, 2011 GF1144 40 1950 ~332 1 PCIe 2.0 x16 1024

2048

 8 384:64:32 822 1645 4008 26.3 52.61 128.27 GDDR5 256 11 4.2 1.1 1263.4 170 7.43 $249
GeForce GTX 560 Ti OEM May 30, 2011 GF1105 40 3000 520 1 PCIe 2.0 x16 1280

2560

 11 352:44:40 732 1464 3800 29.28 32.21 152 GDDR5 320 11 4.2 1.1 1030.7 2106 4.91 OEM
GeForce GTX 560 Ti 448 Cores Limited Edition November 29, 2011 GF1105 40 3000 520 1 PCIe 2.0 x16 1280 14 448:56:40 732 1464 3800 29.28 40.99 152 GDDR5 320 11 4.2 1.1 1311.7 2106 6.25 $289
GeForce GTX 570 December 7, 2010 GF1105 40 3000 520 1 PCIe 2.0 x16 1280 15 480:60:40 732 1464 3800 29.28 43.92 152 GDDR5 320 11 4.2 1.1 1405.4 2196 6.41 $349
GeForce GTX 580 November 9, 2010 GF1105 40 3000[25] 520[25] 1 PCIe 2.0 x16 1536

30727

 16 512:64:48 772 1544 4008 37.06 49.41 192.4 GDDR5 384 11 4.2 1.1 1581.1 2446[26] 6.48 $499
GeForce GTX 590 March 24, 2011 2x

GF110

 40 2x

3000

 2x

520

 2 PCIe 2.0 x16 2x

1536

 2×16 2x

512:64:48

 607 1215 3414 2×29.14 2×38.85 2×163.87 GDDR5 2×384 11 4.2 1.1 2488.3 365 6.82 $699
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Die Count Bus interface Memory (MiB) SM count Config core 1,3 Clock rate Fillrate Memory Configuration API support (version) GFLOPs (FMA)2 TDP (watts)4 GFLOPS/ watt Release Price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) DRAM type Bus width (bit) DirectX OpenGL OpenCL8

[edit] Comparison table: mobile GPUs

[edit] GeForce2 Go series

  • All models are manufactured with a 180 nm manufacturing process
  • All models support DirectX 7.0 and OpenGL 1.2
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce2 Go 100 February 6, 2001 NV11M AGP 4x 8, 16 125 332 2:0:4:2 250 250 500 0 1.328 DDR 32
GeForce2 Go November 11, 2000 NV11M AGP 4x 16, 32 143 166
332		 2:0:4:2 286 286 572 0 2.656 SDR
DDR		 128
64
GeForce2 Go 200 February 6, 2001 NV11M AGP 4x 16, 32 143 332 2:0:4:2 286 286 572 0 2.656 DDR 64

[edit] GeForce4 Go series

  • All models are manufactured with a 150 nm manufacturing process
Model Launch Code name Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce4 Go 410 February 6, 2002 NV17M AGP 8X 16 200 200 2:0:4:2 400 400 800 0 1.6 SDR 64 7.0 1.2
GeForce4 Go 420 February 6, 2002 NV17M AGP 8X 32 200 400 2:0:4:2 400 400 800 0 3.2 DDR 64 7.0 1.2
GeForce4 Go 440 February 6, 2002 NV17M AGP 8X 64 220 440 2:0:4:2 440 440 880 0 7.04 DDR 128 7.0 1.2
GeForce4 Go 460 October 14, 2002 NV17M AGP 8X 64 250 500 2:0:4:2 500 500 1000 0 8 DDR 128 7.0 1.2
GeForce4 Go 4200 November 14, 2002 NV28M AGP 8X 64 200 400 4:2:8:4 800 800 1600 100 6.4 DDR 64 8.1 1.3

[edit] GeForce FX Go 5 (Go 5xxx) series

The GeForce FX Go 5 series for notebooks architecture.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support (version) TDP (watts) Features
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Hardware Drivers (Software)
GeForce FX Go 5100* March 2003 NV34M 150 AGP x8 64 300 600 1:2:2:2 *:4:4:4 1.2 1.2 4.8 DDR 64 9.0 1.5 2.1** Unknown
GeForce FX Go 5200* March 2003 NV34M 150 AGP x8 128 300 600 1:2:2:2 *:4:4:4 1.2 1.2 9.6 DDR 128 9.0 1.5 2.1** Unknown
GeForce FX Go 5600* March 2003 NV31M 130 AGP x8 128 350 600 1:2:2:2 *:4:4:4 1.4 1.4 9.6 DDR 128 9.0 1.5 2.1** Unknown
GeForce FX Go 5650* March 2003 NV31M 130 AGP x8 128 350 600 1:2:2:2 *:4:4:4 1.4 1.4 9.6 DDR 128 9.0 1.5 2.1** Unknown
GeForce FX Go 5700* February 1, 2005 NV36M 130 AGP x8 32 450 550 3:2:2:2 *:4:4:4 1.8 1.8 8.8 DDR 128 9.0 1.5 2.1** Unknown

[edit] GeForce Go 6 (Go 6xxx) series

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
GeForce Go 6100 + nForce Go 430 Unknown C51M 110 HyperTransport Up to 128 MB system 425 System Memory 2:1:2:1 850 425 850 106.25 System Memory DDR2 64/128
GeForce Go 6150 + nForce Go 430 Unknown C51M 110 HyperTransport Up to 128 MB system 425 System Memory 2:1:2:1 850 425 850 106.25 System Memory DDR2 64/128
GeForce Go 6200 Unknown NV44M 110 PCI-E x16 16 300 600 4:3:4:2 1200 600 1200 225 2.4 DDR 32
GeForce Go 6400 Unknown NV44M 110 PCI-E x16 16 400 700 4:3:4:2 1600 800 1600 250 5.6 DDR 64
GeForce Go 6600 Unknown NV43M 110 PCI-E x16 128 300 700 8:3:8:4 3000 1500 3000 281.25 11.2 DDR 128
GeForce Go 6800 November 8, 2004 NV41M 130 PCI-E x16 128 300 700
1100		 12:5:12::12 3000 1500 3000 375 22.4
35.2		 DDR, DDR2
DDR3		 256
GeForce Go 6800 Ultra February 24, 2005 NV41M 130 PCI-E x16 256 450 700
1100		 12:5:12::12 5400 3600 5400 562.5 22.4
35.2		 DDR, DDR2
DDR3		 256

[edit] GeForce Go 7 (Go 7xxx) series

The GeForce Go 7 series for notebooks architecture.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support (version) TDP (watts) Features
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 7000M February 1, 2006 MCP67MV 90 Hyper Transport Up to 256 from system memory 350 System Memory 1:2:2:2 0.7 0.7 System Memory DDR2 64/128 9.0c 2.1 Unknown
GeForce 7150M February 1, 2006 MCP67M 90 Hyper Transport Up to 256 from system memory 425 System Memory 1:2:2:2 0.85 0.85 System Memory DDR2 64/128 9.0c 2.1 Unknown
GeForce Go 72002 Jan 2006 G72M 90 PCIe x16 64 450 700 3:4:4:1 0.45 1.8 2.8 GDDR3 32 9.0c 2.1 Unknown Transparency Anti-Aliasing
GeForce Go 73002 Jan 2006 G72M 90 PCIe x16 128, 256, 512 350 700 3:4:4:2 0.7 1.4 5.60 GDDR3 64 9.0c 2.1 Unknown Transparency Anti-Aliasing
GeForce Go 74002 Jan 2006 G72M 90 PCIe x16 64, 256 450 900 3:4:4:2 0.9 1.8 7.20 GDDR3 64 9.0c 2.1 Unknown Transparency Anti-Aliasing
GeForce Go 7600 Mar 2006 G73M 90 PCIe x16 256, 512 450 1000 5:8:8:8 3.6 3.6 16 GDDR3 128 9.0c 2.1 Unknown Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7600 GT 2006 G73M 90 PCIe x16 256 500 1200 5:12:12:8 4 6 19.2 GDDR3 128 9.0c 2.1 Unknown Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7700 2006 G73-N-B1 80 PCIe x16 512 450 1000 5:12:12:8 3.6 5.4 16 GDDR3 128 9.0c 2.1 Unknown Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7800 March 3, 2006 G70M 110 PCIe x16 256 400 1100 6:16:16:8 3.2 6.4 35.2 GDDR3 256 9.0c 2.1 35 Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7800 GTX Oct 2005 G70M 110 PCIe x16 256 400 1100 8:24:24:16 6.4 9.6 35.2 GDDR3 256 9.0c 2.1 65 Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7900 GS Apr 2006 G71M 90 PCIe x16 256 375 1000 7:20:20:16 6 7.5 32.0 GDDR3 256 9.0c 2.1 20 Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7900 GTX Apr 2006 G71M 90 PCIe x16 256/512 500 1200 8:24:24:16 8 12 38.4 GDDR3 256 9.0c 2.1 45 Scalable Link Interface (SLI), Transparency Anti-Aliasing
GeForce Go 7950 GTX Oct 2006 G71M 90 PCIe x16 512 575 1400 8:24:24:16 9.2 13.8 44.8 GDDR3 256 9.0c 2.1 45 Scalable Link Interface (SLI), Transparency Anti-Aliasing

[edit] GeForce 8M (8xxxM) series

The GeForce 8M series for notebooks architecture.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 8200M G June 2008 MCP77MV, MCP79MVL 80 Integrated (PCIe 2.0 x16) Up to 256 from system memory 8:8:4 400 800 800
1066
(system memory)		 1.6 3.2 12.8
17.056		 DDR2
DDR3		 128 10.0 3.3 19.2 Unknown Unknown PureVideo HD with VP3, Full H.264 / VC-1 / MPEG-2 HW Decode
GeForce 8400M G May 2007 NB8M(G86) 80 PCIe x16 128 / 256 8:8:4 400 800 800 1.6 3.2 6.4 DDR2 / GDDR3 64 10.0 3.3 19.2 10 1.92 PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8400M GS May 2007 NB8M(G86) 80 PCIe x16 128 / 256 16:8:4 400 800 800 1.6 3.2 6.4 DDR2 / GDDR3 64 10.0 3.3 38.4 11 3.49 PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8400M GT May 2007 NB8M(G86) 80 PCIe x16 256 / 512 16:8:4 450 900 1200 1.8 3.6 19.2 DDR2 / GDDR3 128 10.0 3.3 43.2 14 3.09 PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8600M GS May 2007 NB8P(G84) 80 PCIe x16 256 / 512 16:8:4 600 1200 1400 2.4 4.8 22.4 DDR2 / GDDR3 128 10.0 3.3 57.6 20 2.88 PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8600M GT May 2007 NB8P(G84) 80 PCIe x16 256 / 512 32:16:8 475 950 800 / 1400 3.8 7.6 12.8 / 22.4 DDR2 / GDDR3 128 10.0 3.3 91.2 20 4.56 PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8700M GT June 2007 NB8P(G84) 80 PCIe x16 256 / 512 32:16:8 625 1250 1600 5 10 25.6 GDDR3 128 10.0 3.3 120 29 4.14 Scalable Link Interface, PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8800M GTS November 2007 NB8P(G92) 65 PCIe 2.0 x16 512 64:32:16 500 1250 1600 8 16 51.2 GDDR3 256 10.0 3.3 240 50 4.8 Scalable Link Interface, PureVideo HD with VP2, BSP Engine, and AES128 Engine
GeForce 8800M GTX November 2007 NB8P(G92) 65 PCIe 2.0 x16 512 96:48:16 500 1250 1600 8 24 51.2 GDDR3 256 10.0 3.3 360 65 5.54 Scalable Link Interface, PureVideo HD with VP2, BSP Engine, and AES128 Engine

[edit] GeForce 9M (9xxxM) series

The GeForce 9M series for notebooks architecture.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 9100M G
mGPU		 2008 MCP77MH, MCP79MH 65 Integrated
(PCIe 2.0 x16)		 Up to 256 from system memory 8:8:4 450 1100 1066
(system memory)		 1.8 3.6 17.056 DDR3 128 10.0 3.3 26.4 12 2.2 Similar to 8400M G
GeForce 9200M GS 2008 NB9M-GE(G98) 65 PCIe 2.0 x16 256 8:8:4 550 1300 1400 2.2 4.4 11.2 DDR2/GDDR3 64 10.0 3.3 31.2 13 2.4
GeForce 9300M G 2008 NB9M-GE(G86) 80 PCIe 2.0 x16 256/512 16:8:4 400 800 1200 1.6 3.2 9.6 DDR2/GDDR3 64 10.0 3.3 38.4 13 2.95
GeForce 9300M GS 2008 NB9M-GE(G98) 65 PCIe 2.0 x16 256/512 8:8:4 550 1400 1400 2.2 4.4 11.2 DDR2/GDDR3 64 10.0 3.3 33.6 13 2.58
GeForce 9400M G October 15, 2008 MCP79MX 65 Integrated(PCIe 2.0 x16) Up to 256 from system memory 16:8:4 450 1100 800
1066
(system memory)		 1.8 3.6 12.8
17.056		 DDR2
DDR3		 128 10.0 3.3 54 12 4.5 PureVideo HD with VP3. Known as the GeForce 9400M in Apple systems[27] and Nvidia ION based systems
GeForce 9500M G 2008 NB9P(G96) 65 PCIe 2.0 x16 512 16:8:8 500 1250 1600 4 4 25.6 DDR2 / GDDR3 128 10.0 3.3 60 20 3.0
GeForce 9500M GS 2008 NB9P-GV(G96) 80 PCIe x16 512 32:16:8 475 950 1400 3.8 7.6 22.4 DDR2 / GDDR3 128 10.0 3.3 91.2 20 4.56 Rebranded 8600M GT
GeForce 9600M GS 2008 NB9P-GE2(G96) 65 PCIe 2.0 x16 1024 32:16:8 430 1075 800
1600		 3.44 6.88 12.8
25.6		 DDR2
GDDR3		 128 10.0 3.3 103.2 20 5.16
GeForce 9600M GT 2008 NB9P-GS(G96) 65 PCIe 2.0 x16 512/1024 32:16:8 500 1250 1600 4 8 25.6 DDR2 / GDDR3 128 10.0 3.3 120 23 5.22
GeForce 9650M GS 2008 NB9P-GS1(G84) 80 PCIe 2.0 x16 512 32:16:8 625 1250 1600 5 10 25.6 GDDR3 128 10.0 3.3 120 29 4.14 Rebranded 8700M GT
GeForce 9650M GT 2008 NB9P-GT(G96) 65/55 PCIe 2.0 x16 1024 32:16:8 550 1325 1600 4.4 8.8 25.6 GDDR3 128 10.0 3.3 127.2 23 5.53
GeForce 9700M GT July 29, 2008 NB9E-GE(G96) 65 PCIe x16 512 32:16:8 625 1550 1600 5 10 25.6 GDDR3 128 10.0 3.3 148.8 45 3.31
GeForce 9700M GTS July 29, 2008 NB9E-GS(G94) 65 PCIe 2.0 x16 512 48:24:16 530 1325 1600 8.48 12.7 51.2 GDDR3 256 10.0 3.3 190.8 60 3.18
GeForce 9800M GS 2008 NB9E-GT(G94) 65 PCIe 2.0 x16 512 64:32:16 530 1325 1600 8.48 16.96 51.2 GDDR3 256 10.0 3.3 254 60 4.23 Down Clocked 9800M GTS Via Firmware
GeForce 9800M GTS July 29, 2008 NB9E-GT(G94) 65/55 PCIe 2.0 x16 512 / 1024 64:32:16 600 1500 1600 9.6 19.2 51.2 GDDR3 256 10.0 3.3 288 75 3.84
GeForce 9800M GT July 29, 2008 NB9E-GT2(G92) 65/55 PCIe 2.0 x16 512 96:48:16 500 1250 1600 8 24 51.2 GDDR3 256 10.0 3.3 360 65 5.54 Rebranded 8800M GTX
GeForce 9800M GTX July 29, 2008 NB9E-GTX(G92) 65 PCIe 2.0 x16 1024 112:56:16 500 1250 1600 8 28 51.2 GDDR3 256 10.0 3.3 420 75 5.6
Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL GFLOPs (MADD/MUL) TDP (Watts) GFLOPS/ watt Notes
Clock speed Fillrate Memory API support (version)

[edit] GeForce 100M (1xxM) series

The GeForce 100M series for notebooks architecture. (103M, 105M, 110M, 130M are rebranded GPU i.e. using the same GPU cores of previous generation, 9M, with promised optimisation on other features)

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce G 102M January 8, 2009 MCP79XT 65 Integrated
(PCIe 1.0 x16)		 Up to 512 from system memory 16:8:4 450? 1000 800
(system memory)		 1.8 3.6 6.4 DDR2 64 10.0 3.3 48 14 3.43 PureVideo HD, CUDA, Hybrid SLI, based on GeForce 9400M G
GeForce G 103M January 1, 2009 N10M-GE1(G98) 65 PCIe 2.0 x16 512 8:8:4 640 1600 1000 2.56 5.12 8 DDR2 64 10.0 3.3 38 14 2.71 PureVideo HD, CUDA, Hybrid SLI, comparable to the GeForce 9300M GS
GeForce G 105M January 8, 2009 N10M-GE1(G98) 65 PCIe 2.0 x16 512 8:8:4 640 1600 1000
1400		 2.56 5.12 8
11		 GDDR2
GDDR3		 64 10.0 3.3 38 14 2.71 PureVideo HD, CUDA, Hybrid SLI, comparable to the GeForce 9300M GS
GeForce G 110M January 8, 2009 N10M-GE1(G96b) 55 PCIe 2.0 x16 1024 16:8:4 400 1000 1000
1400		 1.6 3.2 8
11		 DDR2
GDDR3		 64 10.0 3.3 48 14 3.43 PureVideo HD, CUDA, Hybrid SLI
GeForce GT 120M February 11, 2009 N10P-GV1(G96b) 55 PCIe 2.0 x16 1024 32:16:8 500 1250 1000 4 8 16 DDR2 128 10.0 3.3 110 23 4.78 PureVideo HD, CUDA, Hybrid SLI, Comparable to the 9500M GT and 9600M GT DDR2 (500/1250/400)
GeForce GT 130M January 8, 2009 N10P-GE1(G96b) 55 PCIe 2.0 x16 1024 32:16:8 600 1500 1000
1600		 4.8 9.6 16
25.6		 DDR2
GDDR3		 128 10.0 3.3 144 23 6.26 PureVideo HD, CUDA, Hybrid SLI, comparable to the 9650M GT
GeForce GTS 150M March 3, 2009 N10E-GE1(G94b) 55 PCIe 2.0 x16 1024 64:32:16 400 1000 1600 6.4 12.8 51.2 GDDR3 128 10.0 3.3 192 Unknown Unknown PureVideo HD, CUDA, Hybrid SLI
GeForce GTS 160M March 3, 2009 N10E-GS1(G94b) 55 PCIe 2.0 x16 1024 64:32:16 600 1500 1600 9.6 19.2 51.2 GDDR3 128 10.0 3.3 288 60 4.8 PureVideo HD, CUDA, Hybrid SLI

[edit] GeForce 200M (2xxM) series

The GeForce 200M series for notebooks architecture. The GTX285M as found in the Clevo X8100 Models, and will be the last of the GT200 Mobile Series.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power GFLOPs TDP (watts) GFLOPS/ watt Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce G210M June 15, 2009 GT218 40 PCIe 2.0 x16 512 16:8:4 625 1500 1600 2.5 5 12.8 GDDR3 64 10.1 3.3 72 14 5.14 Lower clocked versions of the GT218 core is also known as Nvidia ION 2
GeForce GT 220M 2009 G96b 55 PCIe 2.0 x16 1024 32:16:8 500 1250 1000
1600		 4 8 16
25.6		 DDR2
GDDR3		 128 10.0 3.3 120 14 8.57 rebranded 9600M GT @55 nm node shrink
GeForce GT 230M June 15, 2009 GT216 40 PCIe 2.0 x16 1024 48:16:8 500 1100 1600 4 8 25.6 GDDR3 128 10.1 3.3 158 23 6.87
GeForce GT 240M June 15, 2009 GT216 40 PCIe 2.0 x16 1024 48:16:8 550 1210 1600 4.4 8.8 25.6 GDDR3 128 10.1 3.3 174 23 7.57
GeForce GTS 250M June 15, 2009 GT215 40 PCIe 2.0 x16 1024 96:32:8 500 1250 3200 4 16 51.2 GDDR5 128 10.1 3.3 360 28 12.86
GeForce GTS 260M June 15, 2009 GT215 40 PCIe 2.0 x16 1024 96:32:8 550 1375 3600 4.4 17.6 57.6 GDDR5 128 10.1 3.3 396 38 10.42
GeForce GTX 260M March 3, 2009 G92b 55 PCIe 2.0 x16 1024 112:56:16 550 1375 1900 8.8 30.8 60.8 GDDR3 256 10.0 3.3 462 65 7.11
GeForce GTX 280M March 3, 2009 G92b 55 PCIe 2.0 x16 1024 128:64:16 585 1463 1900 9.36 37.44 60.8 GDDR3 256 10.0 3.3 562 75 7.49
GeForce GTX 285M February, 2010 G92b 55 PCIe 2.0 x16 1024 128:64:16 600 1500 2000 9.6 38.4 64.0 GDDR3 256 10.0 3.3 576 75 7.68 Higher Clocked Version of GTX280M with new memory

[edit] GeForce 300M (3xxM) series

The GeForce 300M series for notebooks architecture.

  • 1 Unified Shaders (Vertex shader/Geometry shader/Pixel shader) : Texture mapping unit : Render Output unit
  • 2 Each Streaming Multiprocessor(SM) in the chip of G80/GT200 architecture contains 8 SPs and 2 SFUs. Each SP can fulfil up to two single precision operations MAD per clock. Each SFU can fulfil up to four operations SF per clock (these units can also handle single-precision floating-point multiplications per clock). The approximate ratio of operations MAD to operations SF is equal 2:1. The theoretical SP+SFU performance in single-precision floating point operations [FLOPSsp+sfu, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp+sfu ≈ f × n × 3. Alternative formula:FLOPSsp+sfu ≈ f × m × ( 8 SPs * 2 (MAD) + 4 * 2 SFUs ). [m] - SM count.[12][13]

SP - Shader Processor (Unified Shader, CUDA Core), SFU - Special Function Unit, SM - Streaming Multiprocessor, MAD - ADD+MUL.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power2 (GFLOPs) TDP (watts) GFLOPS/ watt
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 305M January 10, 2010 GT218 40 PCIe 2.0 x16 512 16:8:4 525 1150 1400 2.1 4.2 11.2 DDR3
GDDR3		 64 10.1 3.3 55 14 3.93
GeForce 310M January 10, 2010 GT218 40 PCIe 2.0 x16 512 16:8:4 625 1530 1600 2.5 5 12.8 DDR3
GDDR3		 64 10.1 3.3 73 14 5.21
GeForce 315M January 5, 2011 GT218 40 PCIe 2.0 x16 512 16:8:4 606 1212 1600 2.42 4.85 12.8 DDR3
GDDR3		 64 10.1 3.3 58.18 14 4.16
GeForce 320M April 1, 2010 MCP89 40 Integrated
PCIe 2.0 x16		 dedicated video memory: 256 shared
system memory: 1595[28]		 48:16:8 450 950 1066 3.6 7.2 17.056 DDR3 128 10.1 3.3 136.8 20 6.84
GeForce GT 320M January 21, 2010 GT216 40 PCIe 2.0 x16 1024 24:8:8 500 1100 1580 4 4 25.3 DDR3
GDDR3		 128 10.1 3.3 90 14 6.43
GeForce GT 325M January 10, 2010 GT216 40 PCIe 2.0 x16 1024 48:16:8 450 990 1600 3.6 7.2 25.6 DDR3
GDDR3		 128 10.1 3.3 142 23 6.17
GeForce GT 330M January 10, 2010 GT216 40 PCIe 2.0 x16 1024 48:16:8 575 1265 1600 4.6 9.2 25.6 DDR3
GDDR3		 128 10.1 3.3 182 23 7.91
GeForce GT 335M January 7, 2010 GT215 40 PCIe 2.0 x16 1024 72:24:8 450 1080 1600 3.6 10.8 25.6 DDR3
GDDR3		 128 10.1 3.3 233 28? 8.32?
GeForce GTS 350M January 7, 2010 GT215 40 PCIe 2.0 x16 1024 96:32:8 500 1249 3200 4 16 51.2 DDR3
GDDR3
GDDR5		 128 10.1 3.3 360 28 12.86
GeForce GTS 360M January 7, 2010 GT215 40 PCIe 2.0 x16 1024 96:32:8 550 1436 3600 4.4 17.6 57.6 DDR3
GDDR3
GDDR5		 128 10.1 3.3 413 38 10.87

[edit] GeForce 400M (4xxM) series

The GeForce 400M series for notebooks architecture.

  • 1 Unified Shaders (Vertex shader/Geometry shader/Pixel shader) : Texture mapping unit : Render Output unit
  • 2 Each Streaming Multiprocessor(SM) in the GPU of GF100 architecture contains 32 SPs and 4 SFUs. Each Streaming Multiprocessor(SM) in the GPU of GF104/106/108 architecture contains 48 SPs and 8 SFUs. Each SP can fulfil up to two single precision operations FMA per clock. Each SFU can fulfil up to four operations SF per clock. The approximate ratio of operations FMA to operations SF is equal: for GF100 4:1 and for GF104/106/108 3:1. The theoretical shader performance in single-precision floating point operations(FMA) [FLOPSsp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp ≈ f × n × 2. Alternative formula: for GF100 FLOPSsp ≈ f × m × (32 SPs × 2(FMA)) and for GF104/106/108 FLOPSsp ≈ f × m × (48 SPs × 2(FMA)). [m] - SM count. Total Processing Power: for GF100 FLOPSsp ≈ f × m ×(32 SPs × 2(FMA) + 4 × 4 SFUs) and for GF104/106/108 FLOPSsp ≈ f × m × (48 SPs × 2(FMA) + 4 × 8 SFUs) or for GF100 FLOPSsp ≈ f × n × 2.5 and for GF104/106/108 FLOPSsp ≈ f × n × 8 / 3.[15]

SP - Shader Processor (Unified Shader, CUDA Core), SFU - Special Function Unit, SM - Streaming Multiprocessor, FMA - Fused MUL+ADD.

  • 3 Each SM in the GF100 also contains 4 texture address units and 16 texture filtering units. Total for the full GF100 64 texture address units and 256 texture filtering units.[16] Each SM in the GF104/106/108 architecture contains 8 texture filtering units for every texture address unit. The complete GF104 die contains 64 texture address units and 512 texture filtering units, the complete GF106 die contains 32 texture address units and 256 texture filtering units and the complete GF108 die contains 16 texture address units and 128 texture filtering units.
Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power2
(GFLOPs)		 TDP (watts) Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce 410M January 5, 2011 GF119 40 PCIe 2.0 x16 512 48:83:4 575 1150 1600 2.3 4.6 12.8 DDR3 64 11.0 4.2 110.4 12
GeForce GT 415M September 3, 2010 GF108 40 PCIe 2.0 x16 512 48:83:4 500 1000 1600 2 4 25.6 DDR3 128 11.0 4.2 96 <12(GPU only)[29]
GeForce GT 420M September 3, 2010 GF108 40 PCIe 2.0 x16 512 96:163:4 500 1000 1600 2 8 25.6 DDR3 128 11.0 4.2 192 10-23(GPU only)[29]
GeForce GT 425M September 3, 2010 GF108 40 PCIe 2.0 x16 1024 96:163:4 560 1120 1600 2.24 8.96 25.6 DDR3 128 11.0 4.2 215.04 20-23(GPU only)[29]
GeForce GT 435M September 3, 2010 GF108 40 PCIe 2.0 x16 2048 96:163:4 650 1300 1600 2.6 10.4 25.6 DDR3 128 11.0 4.2 249.6 32-35(GPU only)[29]
GeForce GT 445M September 3, 2010 GF106 40 PCIe 2.0 x16 1024
1536		 144:243:16
144:243:24		 590 1180 1600
2500		 9.44
14.16		 14.16 25.6
60		 DDR3
GDDR5		 128
192		 11.0 4.2 339.84 30-35(GPU only)[29]
GeForce GTX 460M September 3, 2010 GF106 40 PCIe 2.0 x16 1536 192:323:24 675 1350 2500 16.2 21.6 60 GDDR5 192 11.0 4.2 518.4 45-50(GPU only)[29]
GeForce GTX 470M September 3, 2010 GF104 40 PCIe 2.0 x16 1536 288:483:24 550 1100 2500 13.2 26.4 60 GDDR5 256 11.0 4.2 633.6 45-50(GPU only)[29]
GeForce GTX 480M May 25, 2010 GF100 40 PCIe 2.0 x16 2048 352:443:32 425 850 2400 13.6 18.7 76.8 GDDR5 256 11.0 4.2 598.4 100(MXM module)
GeForce GTX 485M January 5, 2011 GF104 40 PCIe 2.0 x16 2048 384:643:32 575 1150 3000 18.4 36.8 96.0 GDDR5 256 11.0 4.2 883.2 100(MXM module)

[edit] GeForce 500M (5xxM) series

The GeForce 500M series for notebooks architecture.

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Config core1 Clock speed Fillrate Memory API support (version) Processing Power2
(GFLOPs)		 TDP (watts) Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
GeForce GT 520M January 5, 2011 GF119 40 PCIe 2.0 x16 1024 48:8:4 740 1480 1600 2.96 5.92 12.8 DDR3 64 11.0 4.2 142.08 12
GeForce GT 520MX May 30, 2011 GF119 40 PCIe 2.0 x16 1024 48:8:4 900 1800 1800 3.6 7.2 14.4 DDR3 64 11.0 4.2 172.8 20
GeForce GT 525M January 5, 2011 GF108 40 PCIe 2.0 x16 1024 96:16:4 600 1200 1800 2.4 9.6 28.8 DDR3 128 11.0 4.2 230.4 20-23
GeForce GT 540M January 5, 2011 GF108 40 PCIe 2.0 x16 1024 96:16:4 672 1344 1800 2.688 10.752 28.8 DDR3 128 11.0 4.2 258.048 32-35
GeForce GT 550M January 5, 2011 GF108 40 PCIe 2.0 x16 1024 96:16:4 740 1480 1800 2.96 11.84 28.8 DDR3 128 11.0 4.2 284.16 32-35
GeForce GT 555M January 5, 2011 GF106

GF108		 40 PCIe 2.0 x16 1536
2048
1024		 144:24:16
144:24:16
96:16:4		 590
650
753		 1180
1300
1506		 1800
1800
3138		 14.6
10.4
3		 14.6
15.6
12		 43.2
28.8
50.2		 DDR3
DDR3
GDDR5		 192
128
128		 11.0 4.2 339.84
374.4
289.15		 30-35
GeForce GTX 560M May 30, 2011 GF116 40 PCIe 2.0 x16 1536 192:32:24 775 1550 2500 18.6 24.8 60.0 GDDR5 192 11.0 4.2 595.2 75
GeForce GTX 570M[30] June 28, 2011 GF114 40 PCIe 2.0 x16 1536 336:56:24 575 1150 3000 13.8 32.2 72.0 GDDR5 192 11.0 4.2 772.8 75
GeForce GTX 580M June 28, 2011 GF114 40 PCIe 2.0 x16 2048 384:64:32 620 1240 3000 19.8 39.7 96.0 GDDR5 256 11.0 4.2 952.3 100

[edit] Mobility Quadro

Main article: NVIDIA Quadro
Model Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Shader clock (MHz) Memory clock (MHz) Config core12 Fillrate Memory Processing Power
GFLOPs		 API support (version) TDP (watts) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
Quadro FX 350M G72GLM 90 PCIe 1.0 x16 256 450 450 900 3:4:4:2 0.9 1.8 14.4 GDDR3 128 9.0c 2.1 15
Quadro FX 360M G86M 80 PCIe 1.0 x16 256 400 800 1200 16:8:4 1.6 3.2 9.6 DDR2 64 38.4 10.0 3.3 17
Quadro FX 370M G98M 65 PCIe 1.0 x16 256 550 1400 1200 8:4:4 2.2 2.2 9.6 GDDR3 64 33.6 10.0 3.3 20
Quadro FX 380M GT218M 40 PCIe 2.0 x16 512 625 1530 1600 16:8:4 2.5 5 12.8 GDDR3 64 73.44 10.1 3.3 25
Quadro FX 560M G73GLM 90 PCIe 1.0 x16 512 500 500 1200 5:12:12:8 4 6 19.2 GDDR3 128 9.0c 2.1 35?
Quadro FX 570M G84M 80 PCIe 1.0 x16 512 475 950 1400 32:16:8 3.8 7.6 22.4 GDDR3 128 91.2 10.0 3.3 45
Quadro FX 770M G96M 65 PCIe 1.0 x16 512 500 1250 1600 32:16:8 4 8 25.6 GDDR3 128 25.6 10.0 3.3 35
Quadro FX 880M GT216M 40 PCIe 2.0 x16 1024 550 1210 1600 48:16:8 4.4 8.8 25.6 GDDR3 128 174.24 10.1 3.3 35
Quadro FX 1500M G71GLM 90 PCIe 1.0 x16 512 375 375 1000 8:24:24:16 6 9 32 GDDR3 256 9.0c 2.1 45
Quadro FX 1600M G84M 80 PCIe 1.0 x16 512 625 1250 1600 32:16:8 5 10 25.6 GDDR3 128 120 10.0 3.3 50?
Quadro FX 1700M G96M 65 PCIe 1.0 x16 512 625 1550 1600 32:16:8 5 10 25.6 GDDR3 128 148.8 10.0 3.3 50
Quadro FX 1800M GT215M 40 PCIe 2.0 x16 1024 450 1080 1600
2200		 72:24:8 3.6 10.8 25.6
35.2		 GDDR3
GDDR5		 128 233.28 10.1 3.3 45
Quadro FX 2500M G71GLM 90 PCIe 1.0 x16 512 500 500 1200 8:24:24:16 8 12 38.4 GDDR3 256 9.0c 2.1 45
Quadro FX 2700M G94M 65 PCIe 1.0 x16 512 530 1325 1600 48:24:16 8.48 12.72 51.2 GDDR3 256 190.8 10.0 3.3 65
Quadro FX 2800M G92M 55 PCIe 2.0 x16 1024 500 1250 2000 96:48:16 8 16 64 GDDR3 256 360 10.0 3.3 75
Quadro FX 3500M G71GLM 90 PCIe 1.0 x16 512 575 575 1200 8:24:24:16 9.2 13.8 38.4 GDDR3 256 9.0c 2.1 45
Quadro FX 3600M G92M 65 PCIe 1.0 x16 512 500 1250 1600 64:32:16
96:48:16		 8
8		 16
24		 51.2 GDDR3 256 240
360		 10.0 3.3 70 based on 8800M GTS/
8800M GTX
Quadro FX 3700M G92M 65 PCIe 1.0 x16 1024 550 1375 1600 128:64:16 8.8 35.2 51.2 GDDR3 256 528 10.0 3.3 75
Quadro FX 3800M G92M 55 PCIe 2.0 x16 1024 675 1688 2000 128:64:16 10.8 43.2 64 GDDR3 256 648.192 10.0 3.3 100
Quadro 1000M GF108 40 PCIe 2.0 x16 2048 700 1400 1800 96:16:4 2.8 11.2 28.8 DDR3 128 268.8 11 4.1 45
Quadro 2000M GF106 40 PCIe 2.0 x16 2048 550 1100 1800 192:32:16 8.8 17.6 28.8 DDR3 128 422.4 11 4.1 55
Quadro 3000M GF104 40 PCIe 2.0 x16 2048 450 900 2500 240:40:32 14.4 18 80 GDDR5 256 432 11 4.1 75
Quadro 4000M GF104 40 PCIe 2.0 x16 2048 475 950 2400 336:56:32 15.2 26.6 76.8 GDDR5 256 638.4 11 4.1 100
Quadro 5000M GF100 40 PCIe 2.0 x16 2048 405 810 2400 320:403:32 12.96 16.2 76.8 GDDR5 256 518.4 11 4.1 100
Quadro 5010M GF110GLM 40 PCIe 2.0 x16 4096 450 900 2600 384:48:32 14.4 21.6 83.2 GDDR5 256 691.2 11 4.1 100
Model Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Shader clock (MHz) Memory clock (MHz) Config core12 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL TDP (Watts) Features
Fillrate Memory Processing Power
GFLOPs		 API support (version)

[edit] Mobility Quadro NVS

Main article: NVIDIA Quadro
Model Code name Fab (nm) Bus interface Memory (MiB) Core clock Shader clock (MHz) Memory clock (MHz) Config core12 Fillrate Memory Processing Power
GFLOPs		 API support (version) TDP (watts) Notes
(MHz) (CUDA) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
Quadro NVS 110M G72M 90 PCIe 1.0 x16 up to 512 300 300 600 3:4:4:2 0.6 1.2 4.8 DDR 64 9.0c 2.1 10
Quadro NVS 120M G72GLM 90 PCIe 1.0 x16 up to 512 450 450 700 3:4:4:2 0.9 1.8 5.6 DDR2 64 9.0c 2.1 10
Quadro NVS 130M G86M 80 PCIe 2.0 x16 up to 256 400? 800? 700 8:4:4 1.6? 1.6? 6.4? DDR2 64 19.2 10.0 3.3 10
Quadro NVS 135M G86M 80 PCIe 2.0 x16 up to 256 400 800 1188 16:8:4 1.6 3.2 9.504 GDDR3 64 38.4 10.0 3.3 10
Quadro NVS 140M G86M 80 PCIe 2.0 x16 up to 512 400 800 1200 16:8:4 1.6 3.2 9.6 GDDR3 64 38.4 10.0 3.3 10
Quadro NVS 150M G98M 65 PCIe 2.0 x16 up to 256 530 1300 1400 8:4:4 2.12 2.12 11.2 GDDR3 64 31.2 10.0 3.3 10
Quadro NVS 160M G98M 65 PCIe 2.0 x16 256 580 1450 1400 8:8:4 2.12 4.24 11.2 GDDR3 64 34.8 10.0 3.3 12
Quadro NVS 300M G72GLM 90 PCIe 1.0 x16 up to 512 450 450 1000 3:4:4:2 0.9 1.8 8 DDR2 64 9.0c 2.1 16
Quadro NVS 320M G84M 65 PCIe 2.0 x16 up to 512 575 1150 1400 32:16:8 4.6 9.2 22.4 GDDR3 128 110.4 10.0 3.3 20
Quadro NVS 510M G72GLM 90 PCIe 1.0 x16 up to 1024 500 500 1200 8:24:24:16 8 12 38.4 GDDR3 256 9.0c 2.1 45? based on Go 7900 GTX
Quadro NVS 2100M GT218M 40 PCIe 2.0 x16 up to 512 535 16 1230 1600 16:8:4 2.14 4.28 12.8 GDDR3 64 59.04 10.1 3.3 14
Quadro NVS 3100M GT218M 40 PCIe 2.0 x16 up to 512 600 16 1470 1600 16:8:4 2.4 4.8 12.8 GDDR3 64 70.56 10.1 3.3 14 based on G210M/310M
Quadro NVS 4200M GF119 40 PCIe 2.0 x16 up to 1024 810 48 1620 1600 48:8:4 3.24 6.48 12.8 GDDR3 64 155.52 11 4.1 based on GT 520M
Quadro NVS 5100M GT216M 40 PCIe 2.0 x16 up to 1024 550 1210 1600 48:16:8 4.4 8.8 25.6 GDDR3 128 174.24 10.1 3.3 35

[edit] Comparison table: workstation GPUs

[edit] Quadro

Main article: NVIDIA Quadro
Model Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Shader clock (MHz) Memory clock (MHz) Config core12* Fillrate Memory Processing Power
GFLOPs		 API support (version) TDP (watts) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
Quadro NV10GL 220 AGP 4x 64 135 135 166 0:4:4:4 0.54 0.54 2.66 SDR 128 7 1.2
Quadro2 MXR NV11GL 180 AGP 4x 64 175 175 183 0:2:4:4 0.7 0.7 2.93 SDR 128 7 1.2
Quadro2 EX NV11GL 180 AGP 4x 64 175 175 166 0:2:4:4 0.7 0.7 2.7 SDR 128 7 1.2
Quadro2 PRO NV15GL 150 AGP 4x 64 250 250 400 0:4:8:8 2 2 6.4 DDR 128 7 1.2
Quadro DCC NV20GL 180 AGP 4x 128 200 200 460 1:4:8:8 1.6 1.6 7.4 DDR 128 8 1.4
Quadro4 380XGL NV18GL 150 AGP 8x 128 275 275 513 0:2:4:4 1.1 1.1 8.2 DDR 128 7 1.4
Quadro4 500XGL NV17GL 150 AGP 4x 128 250 250 166 0:2:4:4 1 1 2.7 SDR 128 7 1.4
Quadro4 550XGL NV17GL 150 AGP 4x 64 270 270 400 0:2:4:4 1.08 1.08 6.4 DDR 128 7 1.4
Quadro4 580XGL NV18GL 150 AGP 8x 64 300 300 400 0:2:4:4 1.2 1.2 6.4 DDR 128 7 1.4
Quadro4 700XGL NV25 150 AGP 4x 64 275 275 550 2:4:8:8 2.2 2.2 8.8 DDR 128 8 1.4
Quadro4 750XGL NV25 150 AGP 4x 128 275 275 550 2:4:8:8 2.2 2.2 8.8 DDR 128 8 1.5 Stereo Display
Quadro4 900XGL NV25 150 AGP 4x 128 300 300 650 2:4:8:8 2.4 2.4 10.4 DDR 128 8 1.4 Stereo Display
Quadro4 980XGL NV28GL 150 AGP 8x 128 300 300 650 2:4:8:8 2.4 2.4 10.4 DDR 128 8 1.4 Stereo Display
Quadro FX 500 NV34GL 150 AGP 8x 128 270 270 480 1:2:2:2
*:4:4:4		 1.08 1.08 7.687 DDR 128 9.0 2.0 Stereo Display
Quadro FX 600 NV34GL 150 PCI 256 350 350 800 1:2:2:2
*:4:4:4		 1 1 7.8 DDR 128 9.0 2.0 Stereo Display
Quadro FX 700 NV35GL 150 AGP 8x 128 275 275 275 1:2:2:2
*:4:4:4		 1.1 1.1 4.4 DDR 128 9.0 2.0 Stereo Display
Quadro FX 1000 NV30GL 130 AGP 8x 128 300 300 300 2:4:8:8 2.4 2.4 9.6 DDR2 128 9.0 2.0 Stereo Display
FX 1100 NV36GL 130 AGP 8x 256 425 425 325 3:2:2:2
*:4:4:4		 1.7 1.7 5.2 DDR2 128 9.0 2.0 Stereo Display
Quadro FX 2000 NV30GL 130 AGP 8x 128 400 400 800 2:4:8:8 3.2 3.2 12.8 DDR2 128 9.0 2.0 Stereo Display
Quadro FX 3000 NV35GL 130 AGP 8x 256 400 400 850 3:4:8:8 3.2 3.2 27.2 DDR 256 9.0 2.0 Stereo Display
Quadro FX 3000G NV35GL 130 AGP 8x 256 400 400 850 3:4:8:8 3.2 3.2 27.2 DDR 256 9.0 2.0 Stereo Display, Genlock
Quadro FX 4000 NV40GL 130 AGP 8x 256 375 375 1000 5:12:12:8 3 4.5 32.0 GDDR3 256 486.4 9.0c 2.1 142 Stereo Display
Quadro FX 4000 SDI NV40GL 130 AGP 8x 256 375 375 1000 5:12:12:8 3 4.5 32.0 GDDR3 256 9.0c 2.1 Stereo Display, Genlock
Quadro FX 330 NV37GL 150 PCIe x16 64 250 250 400 2:4:4:2 1 1 3.2 DDR 128 9.0 2.0 21
Quadro FX 330 G72GL 90 PCIe x16 128 550 550 810 3:4:4:2 1.1 1.1 6.48 DDR2 128 9.0c 2.1 21
Quadro FX 370 G86 80 PCIe x16 256 360 720 1000 16:8:4 1.44 2.88 6.4 DDR2 64 34.56 10.0 3.3 35
Quadro FX 370LP G86 80 PCIe x16 256 540 1080 1000 8:8:4 2.16 4.32 8 DDR2 64 25.92 10.0 3.3 25 DMS-59 for two Single Link DVI
Quadro FX 380 G96 65 PCIe 2.0 x16 256 450 1100 1400 16:8:8 3.6 3.6 22.4 GDDR3 128 52.8 10.0 3.3 34 Two Dual Link DVI, no DisplayPort
Quadro FX 380LP GT218GL 40 PCIe 2.0 x16 512 589 1402 1600 16:8:4 2.356 4.712 12.8 GDDR3 64 67.296 10.1 3.3 28 DisplayPort, Dual Link DVI
Quadro FX 470 MCP7A-U 65 PCIe 2.0 x16
(Integrated)		 Up to 256MB from system memory. 580 1400 800
(system memory)		 16:8:4 2.32 4.64 12.8 DDR2 128 67.2 10.0 3.3 30 based on GeForce 9400 mGPU
Quadro FX 540 NV43GL 90 PCIe x16 128 300 300 550 4:8:8:8 2.4 2.4 8.8 GDDR3 128 9.0c 2.1 35
Quadro FX 550 NV43GL 90 PCIe x16 128 360 360 800 4:8:8:8 2.88 2.88 12.8 GDDR3 128 9.0c 2.1 25
Quadro FX 560 G73GL 90 PCIe x16 128 350 350 1200 5:12:12:8 2.8 4.2 19.2 GDDR3 128 9.0c 2.1 30
Quadro FX 570 G84GL 80 PCIe x16 256 460 920 800 16:8:8 3.68 3.68 12.8 DDR2 128 44.1 10.0 3.3 38
Quadro FX 580 G96 65 PCIe 2.0 x16 512 450 1125 1600 32:16:8 3.6 7.2 25.6 GDDR3 128 108 10.0 3.3 40 Dual DisplayPort, Dual Link DVI
Quadro FX 1300 NV41 130 PCIe x16 128 350 350 550 3:8:8:8 2.8 2.8 8.8 DDR 256 9.0c 2.1 55
Quadro FX 1400 NV41 130 PCIe x16 128 350 350 600 5:12:12:8 2.8 4.2 19.2 DDR 256 9.0c 2.1 70 Stereo Display, SLI
Quadro FX 1500 G71 90 PCIe x16 256 375 375 800 7:20:20:16 6 7.5 40.0 GDDR3 256 9.0c 2.1 65
Quadro FX 1700 G84GL 80 PCIe x16 512 460 920 800 32:16:8 3.68 7.36 12.8 DDR2 128 88.32 10.0 3.3 42
Quadro FX 1800 G100GL-U(G94) 65 PCIe 2.0 x16 768 550 1375 1600 64:32:12 6.6 17.6 38.4 GDDR3 192 264 10.0 3.3 59 Stereo DP Dual Link DVI, Dual DisplayPort, SLI
Quadro FX 3400 NV45GL 130 PCIe x16 256 350 350 900 6:16:16:16 5.6 5.6 28.8 GDDR3 256 9.0c 2.1 101 Stereo display, SLI
Quadro FX 3450 NV41 130 PCIe x16 256 425 425 1000 5:12:12:8 3.4 5.1 32.0 GDDR3 256 9.0c 2.1 83 Stereo display, SLI
Quadro FX 3500 G71GL 90 PCIe x16 256 470 470 1320 7:20:20:16 7.52 9.4 42.2 GDDR3 256 9.0c 2.1 80 Stereo display, SLI
Quadro VX 200 G92 65 PCIe 2.0 x16 512 500 1250 1600 112:56:16 8 28 51.2 GDDR3 256 420 10 3.3 75 2× Dual-link DVI, optimised for Autodesk AutoCAD
Quadro FX 3700 G92 65 PCIe 2.0 x16 512 500 1250 1600 112:56:16 8 28 51.2 GDDR3 256 420 10.0 3.3 78 Stereo display, SLI
Quadro FX 3800 GT200GL 55 PCIe 2.0 x16 1024 602 1204 1600 192:64:16 9.632 38.528 51.2 GDDR3 256 693.504 10.0 3.3 108 Stereo DP Dual Link DVI, Dual DisplayPort, SLI
Quadro FX 4500 G70 110 PCIe x16 512 470 470 1050 8:24:24:16 7.52 11.28 33.6 GDDR3 256 9.0c 2.1 109 Stereo display, SLI, Genlock
Quadro FX 4500X2 G70 110 PCIe x16 1024 470 470 1050 2x 8:24:24:16 15.04 22.56 33.6 GDDR3 256 9.0c 2.1 145 Stereo display, Genlock
Quadro FX 4500 SDI G70 110 PCIe x16 512 470 470 1050 8:24:24:16 7.52 11.28 33.6 GDDR3 256 9.0c 2.1 116 Stereo display, Genlock
Quadro FX 46002 G80 90 PCIe x16 768 500 1200 1400 96:24:24 12 24 67.2 GDDR3 384 345 10.0 3.3 134 Stereo display, SLI, Genlock
Quadro FX 4600 SDI2 G80 90 PCIe x16 768 500 1200 1400 96:24:24 12 24 67.2 GDDR3 384 345 10.0 3.3 154 Stereo display, SLI, Genlock
Quadro FX 4700X2 2xG92 65 PCIe 2.0 x16 2x1024 500 1250 1600 2x(128:64:16) 2x8 2x32 2x51.2 GDDR3 2x256 2x480 10.0 3.3 226
Quadro CX[31] GT200GL 55 PCIe 2.0 x16 1536 602 1204 1600 192:64:24 14.448 38.528 76.8 GDDR3 384 693.504 10.0 3.3 150 Display Port and dual-link DVI Output, optimised for Adobe Creative Suite 4
Quadro FX 4800 GT200GL 55 PCIe 2.0 x16 1536 602 1204 1600 192:64:24 14.448 38.528 76.8 GDDR3 384 693.504 10.0 3.3 150 Stereo DP Dual Link DVI, Dual DisplayPort, SLI
Quadro FX 5500 G71 90 PCIe x16 1024 700 700 1050 8:24:24:16 11.2 16.8 33.6 GDDR3 256 9.0c 2.1 96 Stereo display, SLI, Genlock
Quadro FX 5500 SDI G71 90 PCIe x16 1024 700 700 1050 8:24:24:16 11.2 16.8 33.6 GDDR3 256 9.0c 2.1 104 Stereo display, SLI, Genlock
Quadro FX 56002 G80 90 PCIe 2.0 x16 1536 600 1350 1600 128:32:24 14.4 38.4 76.8 GDDR3 384 518.4 10.0 3.3 171 Stereo display, SLI, Genlock
Quadro FX 5800 GT200GL 55 PCIe 2.0 x16 4096 648 1296 1600 240:80:32 20.736 51.840 102.4 GDDR3 512 933.12 10.0 3.3 189 Stereo DP two Dual Link DVI, DisplayPort, SLI
Quadro 400 GT216GL 40 PCIe 2.0 x16 512 1600 48:16:8 12.8 GDDR3 64 10.1 3.3 32 DisplayPort, Dual Link DVI
Quadro 600 GF108GL 40 PCIe 2.0 x16 1024 640 1280 1600 96:164:4 2.56 10.24 25.6 GDDR3 128 245.76 11 4.1 40 DisplayPort, Dual Link DVI
Quadro 2000 GF106GL 40 PCIe 2.0 x16 1024 625 1250 2600 192:324:16 10 20 41.6 GDDR5 128 480 11 4.1 62 Stereo DP Dual Link DVI, Dual DisplayPort
Quadro 4000 GF100 40 PCIe 2.0 x16 2048 475 950 2800 256:324:32 15.2 15.2 89.6 GDDR5 256 486.4 11 4.1 142
Quadro 5000 GF100 40 PCIe 2.0 x16 2560 513 1026 3000 352:444:40 20.53 22.572 120 GDDR5 320 722.304 11 4.1 152
Quadro 6000 GF100 40 PCIe 2.0 x16 6144 574 1148 3000 448:564:48 27.552 32.144 144 GDDR5 384 1028.608 11 4.1 225
Quadro Plex 7000 40 PCIe 2.0 x16 6144x2 Model Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Shader clock (MHz) Memory clock (MHz) Config core12* Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL TDP (Watts) Features
Fillrate Memory Processing Power
GFLOPs		 API support (version)

[edit] Quadro NVS

Main article: NVIDIA Quadro
Model Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Shader clock (MHz) Memory clock (MHz) Config core12* Fillrate Memory Processing Power
GFLOPs		 API support (version) TDP (watts) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
NVS 50 NV18 150 AGP 4x/PCI 0:2:4:2 DDR 128 7 1.2 DVI-I, S-Video
NVS 100 NV17 150 AGP 4x/PCI 64 333 0:2:4:2 5.328 DDR 128 7 1.2 2x DVI-I, VGA, S-Video
NVS 200 NV17 150 AGP 4x/PCI 0:2:4:2 DDR 128 7 1.2 LFH-60
NVS 210s MCP51 90 Integrated Up to 256 from system memory 1:2:2:1 DDR 128 9.0c 1.2 DVI + VGA
NVS 280 NV34GL 150 PCI-Express ×16/AGP 8× / PCI 0:2:4:2/
1:2:2:2 *:4:4:4		 275/250 DDR 128 9.0 1.5 13 DMS-59
NVS 285 NV44 110 PCI-Express ×1/×16 128 3:4:4:2 DDR 128 9.0 2.1 18 DMS-59
NVS 290 G86 80 PCI-Express ×1/×16 256 460 920 800 16:8:4 1.84 3.68 6.4 DDR2 64 44.16 10 3.3 21 DMS-59
NVS 295 G98 65 PCI-Express ×1/×16 256 550 1300 1400 8:8:4 2.2 4.4 11.2 GDDR3 64 31.2 10 3.3 23 2× DisplayPort or 2× DVI-D
NVS 300 GT218 40 PCI-Express ×1/×16 512 589 1402 1580 16:8:4 2.356 4.712 12.64 DDR3 64 67.3 10.1 3.3 17.5 DMS-59
NVS 400 2× NV17 150 AGP 2× 64 333 2× 0:2:4:2 DDR 2× 128 2× 5.328 DMS-59
NVS 420 2×G98 65 PCI-Express ×1/×16 2×256 550 1300 1400 2× 8:8:4 2× 2.2 2× 4.4 2×11.2 GDDR3 2×64 2× 31.2 10 3.3 40 through VHDCI to (4× DisplayPort or 4× DVI-D)
NVS 450 2×G98 65 PCI-Express ×16 2×256 550 1300 1400 2× 8:8:4 2× 2.2 2× 4.4 2×11.2 GDDR3 2×64 2× 31.2 10 3.3 35 4× DisplayPort or 4× DVI-D

[edit] Tesla

Main article: NVIDIA Tesla
  • 1 Specifications not specified by NVIDIA assumed to be based on the GeForce 8800GTX
  • 2 Specifications not specified by NVIDIA assumed to be based on the GeForce GTX 280
  • 3 Specifications not specified by NVIDIA are assumed to be based on the GeForce 400 Series
  • 4 With ECC on, a portion of the dedicated memory is used for ECC bits, so the available user memory is reduced by 12.5%. (e.g. 3 GB total memory yields 2.625 GB of user available memory.)
  • 5 Fermi implements the new fused multiply–add (FMA) instruction for both 32-bit single-precision and 64-bit double-precision floating point numbers (GT200 supported FMA only in double precision) that improves upon multiply–add by retaining full precision in the intermediate stage.[32]
  • 6 Specifications not specified by NVIDIA assumed to be based on the Quadro FX 5800
  • For the basic specifications of Tesla, refer to the GPU Computing Processor specifications.
  • Due to Tesla's non-output nature, Fillrate and Graphics API compatibility are not applicable.
Configuration Model Archi-
tecture		 # of GPUs Core clock
(MHz)		 Shaders Memory Processing Power (peak)
GFLOPs[33]		 Compute capability TDP (watts) Notes/Form factor
Thread Processors
(total)		 Clock (MHz) Bus type Bus width
(bit)		 Memory
(MB)		 Clock (MHz) Bandwidth
(total)
(GB/s)		 Single Precision(SP) Total(MUL+ADD+SF) Single Precision(SP) MAD(MUL+ADD) Double Precision(DP) FMA
GPU Computing Processor C8701 G80 1 600 128 1350 GDDR3 384 1536 1600 76.8 518.4 345.6 0 1.0 170.9 Internal GPU
(Full-height card)
Deskside Supercomputer D8701 G80 2 600 256 1350 GDDR3 384 2x1536 1600 153.6 2 x 518.4 2 x 345.6 0 1.0 520 Deskside External GPUs
GPU Computing Server S8701 G80 4 600 512 1350 GDDR3 384 4x1536 1600 307.2 4 x 518.4 4 x 345.6 0 1.0 1U Rackmount External GPUs
GPU Computing Processor C10602 GT200 1 602 240 1300 GDDR3 512 4096 1600 102.4 933.12 622.08 77.76 1.3 187.8 Internal GPU
(Full-height card)
Quadro Plex Visual Computing System 2200 D26 GT200GL 2 648 2 x 240 (480) 1296 GDDR3 512 2 x 4096 (8192) 1600 2 x 102.4 2 x 933.12 2 x 622.08 2 x 77.76 1.3 4 dual-link DVI
Deskside or 3U rackmount
Quadro Plex Visual Computing System 2200 S46 GT200GL 4 648 4 x 240 (960) 1296 GDDR3 512 4 x 4096 (16384) 1600 4 x 102.4 4 x 933.12 4 x 622.08 4 x 77.76 1.3 display readback Via PCI-Express Gen 2.0
1U server
GPU Computing Server S10702 GT200 4 602 960 1500 GDDR3 512 4x4096 1600 409.6 4147.2 2764.8 345.6 1.3 800 1U Rackmount External GPUs
connect via 2x PCIe (x8 or x16)
GPU Computing Server S10752[34] GT200 4 602 960 1500 GDDR3 512 4x4096 1600 409.6 4147.2 2764.8 345.6 1.3 1U Rackmount External GPUs
connect via 1x PCIe (x8 or x16)
C2050
GPU Computing Processor		 C20503 GF100 1 575 448 1150 GDDR5 384 30724 3000 144 1288 1030.45 515.2 2.0 238 Internal GPU
(Full-height card)
C2070
GPU Computing Processor		 C20703 GF100 1 575 448 1150 GDDR5 384 61445 3000 144 1288 1030.46 515.2 2.0 247 Full-height video card
IEEE 754-2008 FMA capabilities
C2075
GPU Computing Module		 C2075 GF100 1 575 448 1150 GDDR5 384 6144 3000 144 1288 1030.46 515.2 2.0 225 Full-height video card
IEEE 754-2008 FMA capabilities
M2050
GPU Computing Module		 M2050 GF100 1 575 448 1150 GDDR5 384 30725 3092 148.4 1288 1030.46 515.2 2.0 225 Computing Module
IEEE 754-2008 FMA capabilities
M2070/M2070Q[35]
GPU Computing Module		 M2070/M2070Q GF100 1 575 448 1150 GDDR5 384 61445 3132 150.336 1288 1030.46 515.2 2.0 225 Computing Module
IEEE 754-2008 FMA capabilities
M2090
GPU Computing Module		 M2090 GF110 1 650 512 1300 GDDR5 384 61445 3700 177.4 1664 1331.26 665.6 2.0 250 Computing Module
IEEE 754-2008 FMA capabilities
S2050 1U
GPU Computing
System		 S2050 GF100 4 575 4 x 448 (1792) 1150 GDDR5 384 122885 3092 4 x 148.4 (593.6) 5152 4121.66 2060.8 2.0 900 1U Rack
IEEE 754-2008 FMA capabilities

[edit] Comparison table: Console GPUs

Model Launch Code name Fab (nm) Bus interface Memory (MiB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API support
MOperations/s MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
XGPU (XBOX) November 15, 2001 NV2A 150 Integrated 64 233 400 4:2:8:4 932 932 1864 116.5 6.4 DDR 128 8.1 1.4
RSX (PS3) November 11, 2006 G70 90,65, 40 FlexIO 256
Up to 224 system		 500/550 1300 (rated 1400)
400		 24:8:24:8 74800 4400 13200 2200 20.8
15.5 (read), 10.6 (write)		 GDDR3
XDR DRAM		 128
64		 N/A ES 1.1 w/Cg

[edit] See also

[edit] References

  1. ^ Astle, Dave (2003-04-01). "Moving Beyond OpenGL 1.1 for Windows". gamedev.net. http://www.gamedev.net/reference/articles/article1929.asp. Retrieved 2007-11-15. 
  2. ^ a b c http://www.opengl.org/documentation/specs/version2.1/glspec21.pdf OpenGL 2.1 specification, retrieved Jule 18, 2008
  3. ^ http://www.opengl.org/registry/doc/glspec30.20080811.pdf OpenGL 3.0 specification, retrieved August 12, 2008
  4. ^ OpenGL 3.1 specification, retrieved October 1, 2009
  5. ^ OpenGL 3.2 specification, retrieved October 1, 2009
  6. ^ NVIDIA's 1.4 Billion Transistor GPU: GT200 Arrives as the GeForce GTX 280 & 260
  7. ^ NVIDIA's GeForce 8800 (G80): GPUs Re-architected for DirectX 10(page 6 of 29)
  8. ^ a b c Chipset Comparison Table
  9. ^ Nvidia GF8600/8500/8300 details revealed, Theinquirer.net, accessed April 12, 2007.
  10. ^ http://www.computerbase.de/news/hardware/grafikkarten/nvidia/2007/november/zwei-neue-geforce-8800-gts-bis-dezember/
  11. ^ a b Nvidia Corporation (2008). "Nvidia GeForce 9300 GE". http://www.pcinpact.com/affichage/43963-NVIDIA-9600GT-9300GE-9300GS/58125.htm. 
  12. ^ a b NVIDIA's 1.4 Billion Transistor GPU: GT200 Arrives as the GeForce GTX 280 & 260
  13. ^ a b NVIDIA's GeForce 8800 (G80): GPUs Re-architected for DirectX 10 (page 5 0f 29)
  14. ^ GeForce GT 340 Specification
  15. ^ a b siliconmadness.com (2010). "Nvidia Announces Tesla 20 Series". http://www.siliconmadness.com/2009/11/nvidia-announces-tesla-20-series.html. 
  16. ^ a b c NVIDIA's GeForce GTX 480 and GTX 470: 6 Months Late, Was It Worth the Wait?
  17. ^ NVIDIA's GeForce GTX 460: The $200 King
  18. ^ GeForce GTX 580 Power Consumption and Thermals, Published on 9th November 2010 - Note: This is about the GTX 580, NOT the GTX 480.
  19. ^ NVIDIA Fermi Compute Architecture Whitepaper.pdfPDF ( 855KB), page 11 of 22
  20. ^ NVIDIA's GeForce GTX 580: Fermi Refined
  21. ^ …and GF110s real name is: GF100B (and who guesses what GF114 is?), by Carsten on 11/30/2010, www.gpu-tech.org
  22. ^ …and GF110s real name is: GF104B (and who guesses what GF114 is?), by Carsten on 11/30/2010, www.gpu-tech.org
  23. ^ NVIDIA's GeForce GTX 580: Fermi Refined, by Ryan Smith on 11/9/2010, www.anandtech.com
  24. ^ EVGA GeForce GTX 580 3072MB
  25. ^ a b Ryan Smith (November 9, 2010). "NVIDIA's GeForce GTX 580: Fermi Refined". http://www.anandtech.com/show/4008/nvidias-geforce-gtx-580. 
  26. ^ Techpowerup NVIDIA GeForce GTX 580 1536 MB
  27. ^ accessed 22 September 2009
  28. ^ Apple's 13-inch MacBook Pro (Early 2010) Reviewed: Shaking the CPU/GPU Balance
  29. ^ a b c d e f g 400M-Series TDP: An Explanation & Our Findings
  30. ^ http://www.geforce.com/#/Hardware/GPUs/geforce-gtx-570m/specifications
  31. ^ http://www.nvidia.com/object/product_quadro_cx_us.html
  32. ^ NVIDIA Fermi Compute Architecture Whitepaper.pdfPDF (855KiB), Page 13 of 22
  33. ^ Nvidia Announces Tesla 20 Series
  34. ^ Difference between Tesla S1070 and S1075
  35. ^ NVidia Tesla M2050 & M2070/M2070Q Specs Online
  1. Nvidia Corporation (2009). "nVidia GeForce 8200M GPU"

[edit] External links
Retrieved from "http://en.wikipedia.org/w/index.php?title=Comparison_of_Nvidia_graphics_processing_units&oldid=473712982"
Personal tools
Namespaces
Variants
Actions
Navigation
Interaction
Toolbox
Print/export
Languages