TechPowerUp rolled out the latest version of GPU-Z, the popular graphics subsystem information, diagnostic, and monitoring app, which no enthusiast can leave home without. Version 0.8.0 introduces support for a large number of new GPUs, and fixes several bugs. To begin with, GPU-Z 0.8.0 adds full support for GeForce GTX 980 and GTX 970, including a reliable method of extracting BIOS from GeForce "Maxwell" GPUs. Support is also added for Quadro K420, K620, K2000D, K2200, K4200, K5200; and Radeon R5 M240, R5 M255, FirePro W2100, W4100, W8100, FireStream 9270, FirePro 2450. Preliminary support is added for AMD "Topaz" GPU.

GPU-Z 0.8.0 now accurately measures dedicated and dynamic memory usage on Windows 8 and 8.1 systems. A system hang is fixed on systems with AMD "Hawaii" GPUs, when GPU-Z is running alongside an accelerated video playback. GPU-Z now correctly reads the ROP and stream processor counts of AMD "Tonga" GPU, with updated die-size info. Stuttering on systems with CrossFire ULPS is fixed. The change-log details other relevant changes.DOWNLOAD: TechPowerUp GPU-Z 0.8.0 | GPU-Z 0.8.0 ASUS ROG Themed

The change-log follows.

Here are some of the first pictures of an AIC partner branded NVIDIA GeForce GTX 970 graphics card, the Galaxy GTX 970 GC. Spotted across Chinese PC enthusiast forums and social networks, the latest set of leaks cover not just pictures of what the GTX 970 looks like, but also what's under its hood. To begin with, Galaxy's card appears to be built for the high-end market segment. A meaty twin-fan aluminium fin-stack heatsink, coupled by a spacey backplate cover a signature Galaxy blue PCB, holding NVIDIA's new GTX 970 GPU, and 4 GB of GDDR5 memory. The card appears to feature a high-grade VRM that draws power from a combination of 8-pin and 6-pin PCIe power connectors.

A Coolaler.com community member claims to have scored a GeForce GTX 870 sample, ahead of its September 2014 launch. GPU-Z cannot correctly detect the GPU at this point. It is, however, programmed to pull out some details of unknown GPUs. It reads the card's name as "D17U-20" featuring a GPU name "13C2." The Device ID and BIOS fields are conveniently redacted, so we cannot say for sure if this is genuine.

The card's CUDA core count is 1,664. Given how streaming multiprocessors in "Maxwell" GPUs launched so far feature 128 cores, this particular chip features 13. Other features read out are 138 TMUs, 32 ROPs, and a 256-bit wide memory interface, holding 4 GB of GDDR5 memory. The sample features clock speeds of 1051 MHz core, 1178 MHz GPU Boost, and 1753 MHz (7012 MHz GDDR5 effective) memory, yielding 224 GB/s of memory bandwidth. The test-bed including a Core i7-4820K "Ivy Bridge-E" quad-core processor. The card was put through 3DMark 11, in its performance (P) and extreme (X) presets. It scored P11919 points in the performance preset, and X4625 in the extreme preset; which makes the card roughly as fast as a GeForce GTX 780. And these are pre-release drivers, and probably a pre-launch qualification sample altogether. Color us intrigued.

TechPowerUp released the latest version of GPU-Z, the popular PC graphics information, monitoring, and diagnostics utility, which gives you up to date information on your installed graphics processing hardware, and lets you monitor them in real-time. Version 0.7.9 of GPU-Z adds support for several new GPUs, and fixes various outstanding bugs.

To begin with, support is added for new and upcoming GPUs, such as AMD "Tonga," Radeon R9 M275X, FirePro W5100, W9100; NVIDIA GeForce GTX 780 6 GB, GTX 860M, GT 830M, GTX 780M, GT 740, GT 730, GT 720, Quadro NVS 510, FX 380M, GRID K520, and Tesla K40c. Bug fixes include correct release date for Radeon R9 290, more robust NVIDIA PhysX detection, improved fan-speed monitoring on some newer AMD cards, sensor graph overflow/underflow, and fixed French translation.DOWNLOAD: TechPowerUp GPU-Z 0.7.9 | GPU-Z 0.7.9 ASUS ROG Themed

The complete change-log follows.

TechPowerUp released the latest version of GPU-Z, the popular PC graphics diagnostic and monitoring utility, which gives you up to date information of the GPUs installed in your system, and lets you monitor their clock speeds, temperatures, fan-speeds, voltages, dedicated memory usage, among other things. Version 0.7.8 introduces a few handy user-interface features, beginning with the ability to resize the app's window, when the "Sensors" tab is being viewed. With modern graphics cards giving us dozens of sensors to track, throwing in a scroll-bar is making the tab cluttered, and so we decided to give it resizing. The window returns to the normal size when other tabs, such as the main "Graphics Card" tabs are clicked, and remembers your window size preference when you select the "Sensors" tab again. At this time, this feature is available only on our main (non-skinned) version.

Apart from the resizeable window for "Sensors" tab, GPU-Z 0.7.8 adds tested support for AMD Radeon R9 295X2 "Vesuvius," R9 M275, HD 7500G, and FirePro W9000. It also adds support for NVIDIA GeForce GTX TITAN-Z, GTX 745, GTX 880M, GTX 870M, GTX 860M, GTX 850M, GTX 775M, and Quadro NVS 510. Release dates have been fixed for GTX 780 Ti, and GTX TITAN Black.DOWNLOAD: TechPowerUp GPU-Z 0.7.8, GPU-Z 0.7.8 ASUS ROG Themed

The change-log follows.

TechPowerUp rolled out the version 0.7.7 of GPU-Z, the popular graphics sub-system information, monitoring, and diagnostic utility. Hot on the heels of the previous version, the latest version adds a handful new features, support for new GPUs, and fixes a few bugs and inaccuracies. To begin with, GPU-Z 0.7.7 improves support for GPUs based on NVIDIA's "Maxwell" GPU architecture. The CUDA core and TMU counts on upcoming GTX 750 and 750 Ti should correct now. Support for CHiL 8214 voltage controller is improved, for cards running AMD's "Curacao" and "Pitcairn" graphics processors. Along the way, GPU-Z 0.7.7 adds support for NVIDIA GeForce GTX 860M, Tesla K20Xm, and AMD Radeon HD 8210.DOWNLOAD: TechPowerUp GPU-Z 0.7.7 | GPU-Z 0.7.7 with ASUS ROG skin

The change-log follows.

Here are the firs pictures of AIC partner branded GeForce GTX 750 Ti and GTX 750 graphics cards. From the looks of the board design the first two AIC partners that come to mind are Palit and Galaxy. Specifications of the GM107 silicon, on which the two are based, is detailed in our older article with a die-shot. What's new here, however, is that CUDA core counts and clock speeds aren't the only two specifications that separate the GTX 750 Ti from the GTX 750; it's also the standard memory amount. The former will ship with 2 GB of it, while the latter just 1 GB.

British tech publication UK Gaming Computers got their hands on the two cards, and took a peek under the hood using GPU-Z 0.7.6 (which supports the two). It confirms specifications from the older article, and also reveals clock speeds. The GTX 750 Ti features 1085 MHz core, 1163 MHz GPU Boost, and 5.50 GHz (GDDR5-effective) memory, which churns out 88 GB/s of memory bandwidth. The GTX 750, on the other hand, features the same GPU clock speeds, but slightly slower memory, at 5.10 GHz, at which the memory bandwidth is 81 GB/s. The site also put the two through a quick 3DMark 11 run (performance preset). The GTX 750 Ti scored P5963 points, and the GTX 750 scored P5250 points. Since the two are custom design cards, we're not sure if the clock speeds will stick. For all we know, the two could be factory-overclocked. Impressive performance nonetheless.

TechPowerUp released GPU-Z version 0.7.6, the latest version of the popular lightweight graphics subsystem information, monitoring, and diagnostic utility. Version 0.7.6 comes with support for new GPUs, including NVIDIA's upcoming Maxwell architecture. It also introduces the ability to tell the vendor of memory chips on your discrete graphics card, and a reliable new BIOS reading method for NVIDIA GPUs.

To begin with, GPU-Z adds support for NVIDIA's upcoming GeForce GTX TITAN Black, GeForce GTX 750 Ti, GTX 750 (non-Ti), both of which are based on NVIDIA's "Maxwell" micro-architecture, GTX 840M, and new GTX 760 "lite" (192-bit). On the AMD front, it adds support for AMD A-Series "Kaveri" iGPUs, Radeon R7 M265, FireStream 9350, HD 8530M, and HD 8650D. A new Intel Iris Pro 5200 variant is supported.

GPU-Z 0.7.6 comes with a revolutionary new feature, the ability to tell the vendor of the memory chips on your graphics card, so you don't have to take your card apart to tell the same. GPU-Z 0.7.6 also integrates NVIDIA NVFlash to reliably read BIOS of NVIDIA GPUs. Voltage monitoring of GeForce GTX 780 Ti is improved.DOWNLOAD: TechPowerUp GPU-Z 0.7.6 | TechPowerUp GPU-Z 0.7.6 ASUS ROG Edition

The change-log follows.

In the run up to its rumored February 18th launch, GeForce GTX 750 Ti, the first retail GPU based on NVIDIA's next-generation "Maxwell" GPU architecture, the card is finding itself in the hands of more leaky PC enthusiasts, this time, members of Chinese PC enthusiast community site PCOnline. The site used an early driver to test the GTX 750 Ti, which it put through 3DMark 11 (performance preset) and 3DMark Fire Strike. In the former, the card scored P4188 points, and 3170 points in the latter. The test-bed details are not mentioned, but one can make out a stock Core i7-4770K from one of the screenshots. Also accompanying the two is an alleged GPU-Z 0.7.5 screenshot of the GTX 750 Ti, which reads out its CUDA core count as 960. Version 0.7.5 doesn't support GTX 750 Ti, but it has fall-backs that help it detect unknown GPUs, particularly from NVIDIA. Its successor, GPU-Z 0.7.6, which we're releasing later today, comes with support for the chip.

TechPowerUp announced the latest update to GPU-Z, our popular graphics sub-system information, diagnostic, and monitoring utility. Version 0.7.5 introduces support for some of the newly launched GPUs, a handful of bug-fixes, and stability updates. To begin with, GPU-Z 0.7.5 introduces support for six AMD GPUs, including Radeon R7 260, HD 7600A, HD 8850M, HD 8400, HD 8240, HD 7620G; six NVIDIA GPUs, including GeForce 705A, GTX 645, GTX 650 OEM, Grid K260Q, Quadro K5100M, K6000; and GMA (Bay Trail), and HD 4200 from Intel.

TechPowerUp GPU-Z 0.7.5 also addresses a few rare crashes noted when detecting NVIDIA CUDA, or when running NVIDIA Optimus. Voltage monitoring support for graphics cards based on AMD "Bonaire" and "Pitcairn" GPUs is improved. BIOS reading (for extraction or uploading) on graphics cards based on AMD "Mars" and "Oland" GPUs is improved. Developers taking advantage of the shared memory area of GPU-Z for their apps can rejoice with data update frequency restored to 1 second.DOWNLOAD: TechPowerUp GPU-Z 0.7.5 | GPU-Z 0.7.5 ASUS ROG Themed

The complete change-log follows.

TechPowerUp announced GPU-Z 0.7.4, the latest version of the popular PC graphics subsystem information, monitoring, and diagnostics utility. Version 0.7.4 introduces support for several of the recently launched, and upcoming high-end graphics chips, including Radeon R9 290X, Radeon R9 290, and Radeon R9 270; from AMD's stable, and the GeForce GTX 780 Ti from NVIDIA. Among the other chips supported from the two, include the Radeon HD 8280, HD 7310; and GeForce GT 635, and Quadro K3100M.

GPU-Z 0.7.4 also introduces a number of fixes, including accuracy in reporting release date of the Radeon R9 280X, die-size of AMD "Tahiti," ROP counts on Intel "Haswell" and "Ivy Bridge" IGPs. The new GPU-Z also lets you extract video BIOS from AMD Radeon cards even without any driver for the GPU being installed. The mini stress-test that clogs the PCIe bus interface, forcing it to run at maximum possible speeds (thereby giving you an accurate picture of the PCIe configuration), can now be paused by left-clicking the stress render window. A few rare crashes with systems running Intel IGPs, were addressed.DOWNLOAD: TechPowerUp GPU-Z 0.7.4 | GPU-Z 0.7.4 ASUS ROG-themed

The change-log follows.

Radeon R9 290X is looking increasingly good on paper. Most of its rumored specifications, and SEP pricing were reported late last week, but the ones that eluded us were clock speeds. A source that goes by the name Grant Kim, with access to a Radeon R9 290X sample, disclosed its clock speeds, and ran a few tests for us. To begin with, the GPU core is clocked at 1050 MHz. There is no dynamic-overclocking feature, but the chip can lower its clocks, taking load and temperatures into account. The memory is clocked at 1125 MHz (4.50 GHz GDDR5-effective). At that speed, the chip churns out 288 GB/s of memory bandwidth, over its 512-bit wide memory interface. Those clock speeds were reported by the GPU-Z client to us, so we give it the benefit of our doubt, even if it goes against AMD's ">300 GB/s memory bandwidth" bullet-point in its presentation.

Among the tests run on the card include frame-rates and frame-latency for Aliens vs. Predators, Battlefield 3, Crysis 3, GRID 2, Tomb Raider (2013), RAGE, and TESV: Skyrim, in no-antialiasing, FXAA, and MSAA modes; at 5760 x 1080 pixels resolution. An NVIDIA GeForce GTX TITAN was pitted against it, running the latest WHQL driver. We must remind you that at that resolution, AMD and NVIDIA GPUs tend to behave a little differently due to the way they handle multi-display, and so it may be an apples-to-coconuts comparison. In Tomb Raider (2013), the R9 290X romps ahead of the GTX TITAN, with higher average, maximum, and minimum frame rates in most tests.

TechPowerUp announced the latest update to GPU-Z, the popular graphics hardware information, monitoring and diagnostics utility. Version 0.7.3 brings in a few major changes, keeping in mind plans by AMD and NVIDIA to update their product stacks, a little later this year. We've added preliminary support for Radeon R7 240, R7 250, R7 260X, R9 270, R9 270X, R9 290, and R9 290X. On the NVIDIA front, we've added support for GeForce GT 625, GT 645, GT 755M, GT 745M, GTX 760M, GTX 765M, GTX 770M, Quadro K1100M, and K5100M. Support was also added for AMD Radeon HD 7600G, HD 8250, HD 8330, HD 8470G, HD 8570, HD 8570G, and E6460; FirePro W7000, and W600. GPU-Z 0.7.3 brings improved support for GeForce GTX 780 graphics cards with CHiL CHL8318 voltage controllers, and GeForce cards in general, with NCP4206 controllers.DOWNLOAD: TechPowerUp GPU-Z 0.7.3 | TechPowerUp GPU-Z 0.7.3 ASUS ROG-themed

The complete change-log follows.

Since the very first DirectX 10-ready graphics cards by AMD, we've been used to the "Radeon HD xyz0" nomenclature, in which "x" denoted generation, "y" market segment, and "z" variant. That all is about to change with the company's Volcanic Islands GPU family, which will be unveiled (at least to the press), later this month. Using the same "x, y, z" variables as mentioned before, the new nomenclature could look like "Radeon Ry xz i" (where the new variable "i" could denote special features).

An example of this new nomenclature could be, say, Radeon R9 280 X, where "9" denotes the high-end market segment, currently held by Radeon HD 7900 series, "2" indicating generation, and "80" denoting variant. "XT" (full-spec) chips could get the "80" marking, and "Pro" (partial-spec) chips could get the "60" or "70" marking, but it isn't fixed, and could even be "50" and "40" for lower-end parts. At this point, we can't even speculate what the "i" (special feature) could denote. For mobile parts, the letter "M" could be prefixed to the "xz" component of the model number (example: Radeon R9 M380 X). Validations for graphics cards running early drivers with this naming scheme, have been showing up on our GPU-Z Validation database for days now, and our analysis is our best understanding of their naming strings. Capiche? Can't blame you.

TechPowerUp released GPU-Z 0.7.2, the latest version of the popular graphics hardware information, diagnostic, and monitoring utility that enthusiasts and overclockers can't leave home without. Version 0.7.2 adds support for new GPUs, notably NVIDIA's upcoming GeForce GTX 760, and the new Radeon HD 8970M; improves support for Intel HD 4xxx series graphics embedded into Core "Haswell" processors, and a few more user-interface feature additions.

To begin with, GPU-Z 0.7.2 adds support for NVIDIA's GeForce GTX 760, GeForce GT 740M (based on the new GK208 silicon), Tesla K10 compute accelerator; AMD's Radeon HD 8970M, HD 8490, and HD 7400D. Detection and information of Core "Haswell" integrated GPUs, are improved. A new AMD Radeon logo was added, and will show up for AMD-branded Radeon GPUs. Tooltip translations were added for Greek, French (improved), and thanks to our friends at Clube do Hardware, Brazilian Portuguese. A rare crash during DirectCompute detection, is fixed.DOWNLOAD: TechPowerUp GPU-Z 0.7.2, GPU-Z 0.7.2 ASUS ROG-themed

The change-log follows.

There are many theories doing rounds about the specifications of NVIDIA's upcoming performance-segment GPU, the GeForce GTX 760. One states that it's largely similar to the GeForce GTX 660 Ti from previous-generation, with higher clock speeds, possibly 7.00 GHz memory, and GPU Boost; while another suggests a completely new core-configuration. According to a GPU-Z screenshot leaked by a ChipHell community member, NVIDIA is attempting to give the GeForce GTX 660 a successor, rather than merely retrofitting the GTX 660 Ti.

According to leaks that surfaced on ChipHell, NVIDIA is configuring a GK104 GPU with just three out of four GPC (graphics processing clusters) enabled, while keeping the memory and raster operations untouched. This approach would give the chip 1,152 CUDA cores, 96 TMUs, 32 ROPs, and a 256-bit wide GDDR5 memory interface. The card in the GPU-Z screenshot features 1072 MHz core, 1111 MHz GPU Boost, and 7.00 GHz memory.

TechPowerUp announced GPU-Z 0.7.1, the latest version of the popular graphics subsystem information, monitoring, and diagnostic tool. Version 0.7.1 adds support for new GPUs, and an experimental feature that lets you investigate power-capping on some of the newer generations of NVIDIA GPUs (needs GeForce 319.xx or later drivers). To begin with, GPU-Z 0.7.1 introduces support for NVIDIA's upcoming GeForce GTX 780 and GeForce GTX 770 graphics cards, along with support for AMD's new Radeon HD 8000M, HD 8000G, and HD 8000D series GPUs/IGPs, including the HD 8310G, HD 8410G, HD 8450G, HD 8510G, HD 8550G, HD 8610G, and HD 8650G; and a few exotic GPUs, such as GT 730M, GT 750M, GTX 780M, GRID K1, GRID K2, and HD 7730.DOWNLOAD: TechPowerUp GPU-Z 0.7.1 | TechPowerUp GPU-Z 0.7.1 ASUS ROG Themed

The change-log follows.

TechPowerUp released the latest version of GPU-Z, the popular graphics subsystem information, diagnostic, and monitoring utility, which gives you in-depth information about installed graphics hardware, and lets you monitor various parameters in real-time. With version v0.7.0 of GPU-Z, we focused on adding and improving support for new GPUs.

To begin with, it features support for AMD Radeon HD 7990 "Malta" dual-GPU graphics card, along with support for Radeon HD 8550M, HD 7340, HD 7290, and HD 8670D "Richland" on the AMD front; and GeForce GTX 680MX, GTX 675MX, GT 218, and 9400 GT (rare GPUs), on the NVIDIA front. Voltage monitoring is improved on Radeon HD 7790.DOWNLOAD: TechPowerUp GPU-Z 0.7.0 | GPU-Z 0.7.0 ASUS ROG Themed

The change-log follows.

Just ahead of a skirmish between AMD and NVIDIA in the sub-$200 market segment, which could go down later this month, TechPowerUp released GPU-Z v0.6.9, with tested support for the two contenders: AMD Radeon HD 7790, and NVIDIA GeForce GTX 650 Ti with GPU Boost (refresh). In addition, the new GPU-Z version gets you support for Radeon HD 8870M, GeForce GT 415, and GT 750M. For GeForce "Kepler" family GPUs, DirectX feature-set value is fixed. A number of tool-tips are added to key window elements, such as vendor logo, vBIOS extraction, render test, and screen-capture.DOWNLOAD: TechPowerUp GPU-Z v0.6.9 | GPU-Z v0.6.9 with ASUS ROG skin

The change-log follows.

Here are the first pictures of Sapphire Radeon HD 7790 Dual-X, the company's premium offering based on AMD's new GPU. The card features Sapphire's in-house PCB and cooler designs, including an aluminium fin-stack heatsink ventilated by a pair of 80 mm fans, and a 21.5 cm long PCB. The card draws power from a single 6-pin PCIe power connector, its display outputs are similar to the HD 7850, with a pair of DVI connectors, HDMI, and DisplayPort. It can pair with another of its kind, only.

TechPowerUp announced version 0.6.8 of GPU-Z, the popular graphics subsystem information, monitoring, and diagnostic utility, which gives you detailed information about the installed graphics hardware, and lets you monitor key specifications in real-time, such as clock speeds, temperatures, voltages, and video memory usage. Version 0.6.8 introduces support for new GPUs, namely NVIDIA's GeForce GTX Titan, GeForce 505 (GT216), GT 640M, GTX 675MX, Quadro K2000, and K3000; AMD's Radeon HD 7480D, FirePro W8000, V8700, fake HD 6850 (based on HD 6450). GPU load monitoring method on AMD GPUs is improved, and should be more accurate. Several minor bugs were patched.DOWNLOAD: TechPowerUp GPU-Z 0.6.8, TechPowerUp GPU-Z 0.6.8 ASUS ROG Themed

The change-log follows.

TechPowerUp released version 0.6.7 of GPU-Z, the popular graphics subsystem information, monitoring, and diagnostic utility. The new release brings some feature-additions, support for more graphics processors, and stability improvements. To begin with, we made room in the GPU-Z window to display TMU (texture memory unit) count. Support for a large number of recently-launched GPUs, including Radeon HD 7870 "Tahiti LE," mobile GeForce 600 series MX, and from Quadro family, were added.

TechPowerUp GPU-Z 0.6.7 also brings a few UI enhancements. To begin with, GPU-Z remembers window position from its previous session, cutting you time for positioning it right for screenshots. Next up, when minimized, its tray icon does more than just show you the app is running. Its tooltip (visible when hovered), displays some important sensor data. A new "-tab" command line parameter allows proverclockers to script-launch GPU-Z showing a specific tab. Among the bugs fixed are one related to a crash occurring on CrossFire setups (a Catalyst-related bug), another crash occurring on NVIDIA setups when updating sensor data (GeForce driver-related bug), temperature reading on AMD "Llano" APUs is improved.DOWNLOAD: TechPowerUp GPU-Z 0.6.7, TechPowerUp GPU-Z 0.6.7 ASUS ROG Themed

The change-log follows.

TechPowerUp announced the latest version of GPU-Z, version 0.6.6, with a host of stability updates. To begin with, support was added for NVIDIA Tesla M2070 GPU compute accelerator. The issue of main window not displaying correctly with non-standard Windows font DPI settings is fixed. GPU overclock calculation was fixed for pre-Kepler NVIDIA GPUs. Crashes on systems with broken high-precision event timer implementation (HPET) were fixed, and so were several memory leaks.DOWNLOAD: TechPowerUp GPU-Z 0.6.6, TechPowerUp GPU-Z 0.6.6 ASUS ROG Edition

The change-log for this version follows.

TechPowerUp released the latest version of GPU-Z, the popular graphics subsystem information and diagnostic utility. Version 0.6.5 features the biggest complement of changes this year. To begin with GPU-Z can now reliably extract, save, and upload BIOS from NVIDIA GeForce Kepler family of GPUs. Boost clock detection for GeForce Kepler family is improved; and real-time memory clock monitoring for GeForce Kepler GPUs without Boost is fixed. A working ASIC-quality calculation method is implemented for GeForce Kepler GPUs.

GPU clock and temperature readings are improved for AMD "Trinity" APUs, and stability increased. Support is added for a large number of new GPUs, including AMD Radeon HD 7450A, HD 7730M, HD 7700M, FirePro M4000, W5000; NVIDIA GeForce GTX 650 Ti, GT 635M, GT 620M, GeForce 610M, GT 620 (GF119), GT 640 (GF118), Quadro 7000, Quadro K2000M; and Intel 4th Generation Core "Haswell" graphics. Release date and die-size measurements were added for a large number of GPUs. A large number of outstanding bugs were quashed.DOWNLOAD: TechPowerUp GPU-Z 0.6.5 | TechPowerUp GPU-Z 0.6.5 ASUS ROG Edition

The change-log follows.

Here are some of the first pictures of NVIDIA's upcoming GK106 silicon, which goes into building the GeForce GTX 660 graphics card. The GK106, built on the 28 nm silicon fab process, is poised to be NVIDIA's newest mainstream-performance chip that succeeds the GF116. The pictures reveal the chip package to be almost as big as the GF116 but smaller than the GK104. This can be attributed to fewer memory I/O pins (192-bit maximum bus width).

The rectangular die of the GK106 appears to have roughly the same area as that of the GF116, but with the higher transistor density of the 28 nm process, one can expect a significantly higher transistor count for the chip. If some of the pictures we're seeing are any indication the GK106 will be extremely energy-efficient, as an unknown graphics card based on it draws power from just one 6-pin power connector.