Report an Error

NVIDIA GeForce 8800 GTS 640

Graphics Processor
G80
Cores
96
TMUs
24
ROPs
20
Memory Size
640 MB
Memory Type
GDDR3
Bus Width
320 bit
GPU Chip
GPU
The GeForce 8800 GTS 640 was a high-end graphics card by NVIDIA, launched on November 8th, 2006. Built on the 90 nm process, and based on the G80 graphics processor, in its G80-100-K0-A2 variant, the card supports DirectX 11.1. Even though it supports DirectX 11, the feature level is only 10_0, which can be problematic with many DirectX 11 & DirectX 12 titles. The G80 graphics processor is a large chip with a die area of 484 mm² and 681 million transistors. Unlike the fully unlocked GeForce 8800 GTX, which uses the same GPU but has all 128 shaders enabled, NVIDIA has disabled some shading units on the GeForce 8800 GTS 640 to reach the product's target shader count. It features 96 shading units, 24 texture mapping units, and 20 ROPs. NVIDIA has paired 640 MB GDDR3 memory with the GeForce 8800 GTS 640, which are connected using a 320-bit memory interface. The GPU is operating at a frequency of 513 MHz, memory is running at 792 MHz.
Being a dual-slot card, the NVIDIA GeForce 8800 GTS 640 draws power from 1x 6-pin power connector, with power draw rated at 143 W maximum. Display outputs include: 2x DVI, 1x S-Video. GeForce 8800 GTS 640 is connected to the rest of the system using a PCI-Express 1.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 449 US Dollars.

Graphics Processor

GPU Name
G80
GPU Variant
G80-100-K0-A2
Architecture
Tesla
Foundry
TSMC
Process Size
90 nm
Transistors
681 million
Density
1.4M / mm²
Die Size
484 mm²
Chip Package
BGA-1449

Graphics Card

Release Date
Nov 8th, 2006
Generation
GeForce 8
(8800)
Predecessor
GeForce 7 PCIe
Successor
GeForce 9
Production
End-of-life
Launch Price
449 USD
Bus Interface
PCIe 1.0 x16
Reviews
403 in our database

Relative Performance

GeForce 210
23%
GeForce 9400 GT
29%
Radeon HD 4550
36%
Radeon HD 5450
46%
Radeon HD 6450
54%
GeForce GT 520
57%
GeForce GT 220
70%
GeForce GT 430
92%
Radeon HD 5570
93%
GeForce 8800 GTS 640
100%
Radeon HD 4670
101%
GeForce GT 440
107%
GeForce GT 240
109%
GeForce 9600 GT
125%
Radeon HD 5670
133%
GeForce GT 640
142%
GeForce 9800 GT
147%
Radeon HD 6670
153%
Radeon HD 4830
158%
Radeon HD 4770
169%
Radeon HD 4850
178%
GeForce GTS 250
182%
GeForce GTS 450
188%
Radeon HD 5750
194%
Radeon HD 7750
222%
Radeon HD 5770
223%
GeForce GTX 260
227%
Radeon HD 4870
230%
Radeon Vega 8
231%
GeForce GTX 550 Ti
233%
GeForce GTX 650
235%
Radeon HD 5830
248%
Radeon HD 6790
261%
Radeon HD 4890
266%
GeForce GTX 460
276%
Radeon RX Vega 11
278%
GeForce GT 1030
281%
GeForce GTX 275
283%
Radeon HD 7770 GHz Edition
284%
GeForce GTX 280
284%
GeForce GTX 465
290%
Radeon HD 6850
304%
GeForce GTX 285
310%
Radeon HD 5850
332%
GeForce GTX 650 Ti
338%
Radeon HD 7790
338%
Radeon RX 550
353%
GeForce GTX 470
354%
Radeon HD 6870
366%
Radeon HD 5870
391%
GeForce GTX 560 Ti
403%
Radeon HD 4870 X2
405%
GeForce GTX 750 Ti
413%
Radeon HD 6950
415%
GeForce GTX 295
429%
GeForce GTX 650 Ti Boost
434%
Radeon HD 7850
438%
GeForce GTX 480
445%
Radeon HD 6970
466%
Radeon R7 265
475%
Radeon RX 460
482%
Radeon R7 370
483%
GeForce GTX 660
484%
GeForce GTX 570
486%
Radeon RX 560
494%
GeForce GTX 950
524%
Radeon HD 7870 GHz Edition
529%
Radeon R9 270X
542%
GeForce GTX 660 Ti
549%
GeForce GTX 580
551%
GeForce GTX 1050
555%
Radeon HD 7950
557%
GeForce GTX 1630
567%
Radeon HD 5970
568%
GeForce GTX 760
584%
GeForce GTX 670
628%
GeForce GTX 960
645%
Radeon R9 380
661%
Radeon R9 285
665%
Radeon HD 7970
672%
GeForce GTX 680
679%
GeForce GTX 1050 Ti
694%
GeForce GTX 770
712%
Radeon HD 6990
729%
Radeon R9 280X
746%
GeForce GTX 590
757%
Radeon HD 7970 GHz Edition
758%
GeForce GTX 780
839%
Arc A380
840%
Radeon RX 6400
852%
GeForce GTX 1650
869%
Radeon RX 470
923%
Radeon R9 290
936%
Radeon RX 570
987%
Radeon R9 390
999%
Radeon R9 290X
1004%
GeForce GTX 970
1018%
GeForce GTX TITAN
1031%
GeForce GTX 780 Ti
1045%
Radeon R9 390X
1060%
Radeon HD 7990
1064%
Radeon RX 480
1069%
GeForce GTX 690
1078%
GeForce GTX 1060 6 GB
1108%
Radeon RX 5500 OEM
1123%
Radeon RX 580
1136%
Radeon RX 5500 XT
1145%
Radeon RX 6500 XT
1155%
GeForce GTX 980
1160%
GeForce GTX 1650 SUPER
1170%
Radeon R9 FURY
1175%
Radeon RX 590
1227%
Radeon R9 295X2
1292%
GeForce GTX 1660
1300%
Radeon R9 FURY X
1315%
GeForce GTX 980 Ti
1337%
GeForce GTX TITAN X
1372%
GeForce GTX 1660 SUPER
1413%
GeForce GTX 1070
1492%
GeForce GTX 1660 Ti
1492%
GeForce RTX 3050 8 GB
1516%
Radeon RX Vega 56
1588%
GeForce GTX 1070 Ti
1685%
Radeon RX 5600 XT
1710%
Radeon RX Vega 64
1733%
GeForce GTX 1080
1757%
GeForce RTX 2060
1757%
Radeon RX 5700
1829%
Arc A580
1833%
Radeon RX 6600
1909%
GeForce RTX 2060 SUPER
1973%
GeForce RTX 2070
1999%
Radeon RX 5700 XT
2001%
GeForce RTX 3060 12 GB
2040%
Arc A750
2106%
Radeon VII
2118%
TITAN X Pascal
2173%
Radeon RX 6600 XT
2195%
GeForce GTX 1080 Ti
2238%
Arc A770
2260%
GeForce RTX 2070 SUPER
2262%
Radeon RX 6650 XT
2380%
Radeon RX 7600
2406%
GeForce RTX 4060
2417%
GeForce RTX 2080
2433%
Radeon RX 7600 XT
2483%
GeForce RTX 2080 SUPER
2551%
GeForce RTX 3060 Ti
2613%
Radeon RX 6700 XT
2705%
Radeon RX 6750 XT
2871%
GeForce RTX 4060 Ti 8 GB
2903%
GeForce RTX 2080 Ti
2924%
GeForce RTX 3070
3060%
GeForce RTX 3070 Ti
3275%
Radeon RX 7700 XT
3309%
Radeon RX 6800
3373%
GeForce RTX 4070
3738%
Radeon RX 6800 XT
3832%
GeForce RTX 3080
3977%
Radeon RX 7800 XT
4017%
Radeon RX 6900 XT
4129%
GeForce RTX 4070 SUPER
4336%
Radeon RX 7900 GRE
4419%
GeForce RTX 3080 Ti
4455%
Radeon RX 6950 XT
4461%
GeForce RTX 3090
4539%
GeForce RTX 4070 Ti
4653%
GeForce RTX 4070 Ti SUPER
5084%
Radeon RX 7900 XT
5221%
GeForce RTX 3090 Ti
5266%
GeForce RTX 4080
5911%
GeForce RTX 4080 SUPER
6000%
Radeon RX 7900 XTX
6057%
GeForce RTX 4090
7427%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
513 MHz
Shader Clock
1188 MHz
Memory Clock
792 MHz
1584 Mbps effective

Memory

Memory Size
640 MB
Memory Type
GDDR3
Memory Bus
320 bit
Bandwidth
63.36 GB/s

Render Config

Shading Units
96
TMUs
24
ROPs
20
SM Count
12
L2 Cache
80 KB

Theoretical Performance

Pixel Rate
10.26 GPixel/s
Texture Rate
24.62 GTexel/s
FP32 (float)
228.1 GFLOPS

Board Design

Slot Width
Dual-slot
Length
267 mm
10.5 inches
TDP
143 W
Suggested PSU
300 W
Outputs
2x DVI
1x S-Video
Power Connectors
1x 6-pin
Board Number
P356

Graphics Features

DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1 (1.0)
Vulkan
N/A
CUDA
1.0
Shader Model
4.0

G80 GPU Notes

Each Streaming Multiprocessor(SM) in the chip architecture contains 8 SPs and 2 SFUs.

Each SP can fulfill up to two single precision operations MAD per clock.

Each SFU can fulfill 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 formula: FLOPSsp+sfu; f × n × 3.

Alternative formula: FLOPSsp+sfu; f × m × ( 8 SPs * 2 (MAD) + 4 * 2 SFUs ). [m] - SM count.

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

Latest Drivers:
Windows 2000:
Quadro Release 261.19

Windows XP / Server 2003 x64:
GeForce Release 340.52
Quadro Release R319 U2 (321.01)
Tesla Release 258.96

Windows Vista / 7 / 8 / 8.1 / 10 32-bit:
GeForce Release 342.01
Quadro Release R340 U15 (342.01)
Tesla Release 258.96

Retail boards based on this design (1)

Name GPU Clock Memory Clock Other Changes
580 MHz 850 MHz
Oct 6th, 2024 13:18 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts