A Gainward-branded GeForce GTX 670 graphics card went up for pre-order in The Philippines, listed for pre-order for PHP 19,990 (US $470), by Philippine retailer PCHub. The price is backed by "price protection", which as we understand, transacts the difference between launch-price and pre-order listing price with the buyers before shipping (refunds the difference, if the launch price is lower, collects the difference to ship, if the launch price is higher (we doubt), or refunds the pre-order amount). The store sale page doesn't list any other specifications than memory size (2 GB) and memory bus width (256-bit GDDR5). Other specifications of the GTX 670 could be found here (older article).

NVIDIA released its first desktop graphics cards based on its 28 nm GK107 silicon, in as many as three models, the GeForce GT 630, GT 640, GT 640 (second variant). Apart from these, NVIDIA appears to have launched two more models, one labeled GT 640, and another GT 645, which are based on previous generation GF116 and GF114, respectively. These new SKUs are available only to OEM partners, who will implement them in their new desktop PC designs.

Of the five new SKUs, the GT 630 and GT 640 (28 nm) are most interesting, as they are based on the GK107 silicon, with as many as 384 CUDA cores, and TDP as low as 50W. The GT 630 is a single-slot, low-profile graphics card with 384 CUDA cores, and a 128-bit wide GDDR5 memory interface, 875 MHz GPU clock speed, and 891 MHz memory clock speed. The GT 640 (28 nm) features different clock speeds. The specifications may seem confusing to the end user, but then they really don't concern people who buy retail-channel graphics cards. NVIDIA and AMD design OEM-specific SKUs completely à la carte, to OEM partners' requirements.

Even as NVIDIA is on the verge of unveiling its GeForce GTX 690 dual-GPU graphics card, at GeForce LAN Shanghai, AMD is in no hurry. Its competitive graphics card to the GTX 690, the Radeon HD 7990 "New Zealand", will be kept under the wraps till Computex 2012 (early June), DonanimHaber learned. Radeon HD 7990 will pack two completely unlocked 28 nm "Tahiti" GPUs, a total of 4,096 Graphics CoreNext stream processors, 6 GB of GDDR5 memory, and the ability to drive 6-monitor Eyefinity, out of the box.

Although the recent round of price-cuts by AMD covered mainly three SKUs, the HD 7970, HD 7950, and HD 7770; HIS put together its own list of price-cuts covering all Radeon HD 7000 series SKUs launched by it, including its non-reference design and overclocked ones. The new prices (in EUR, incl. taxes) are listed below.

• HIS 7750 iCooler 1GB GDDR5 PCI-E DP/DVI/HDM - 89,- Euro
• HIS 7770 iCooler 1GB GDDR5 PCI-E DVI/HDMI/2xMiniDP - 114,90 Euro
• HIS 7870 IceQ X Turbo 2GB GDDR5 PCI-E DVI/HDMI/2xMini DP - 299 Euro
• HIS 7870 IceQ Turbo 2GB GDDR5 PCI-E DVI/HDMI/2xMini DP - 309,90 Euro

Here are the first pictures of KFA2 GeForce GTX 680 Hall of Fame (HOF) Edition, an exclusive to markets KFA2, Galaxy's Europe brand, has a presence in. British retailer Overclockers UK listed the card for pre-order, it goes for £529.99, including VAT (US $854). The card features non-reference PCB and cooling assembly, its PCB dons a white color, which sets it apart from every other GTX 680 graphics card. The GeForce GTX 680 GPU is accompanied by 2 GB of GDDR5 memory across a 256-bit wide memory interface. The GPU is overclocked out of the box, with base core speed of 1202 MHz, boost core speed of 1267 MHz, and memory speed of 1502 MHz (6008 MHz GDDR5 effective).

The PCB implements bleeding-edge voltage regulation circuitry, that includes CPL-made single-phase chokes, International Rectifier DirectFET, and tantalum capacitors - stuff that's fit for avionics. The VRM is make up of an 8+2+2 phase circuit. The card draws power from two 8-pin PCIe power connectors. A Galaxy GX31 custom controller governs the VRM, providing software voltage control, voltage monitoring and power draw monitoring over SMBUS. The cooling solution is Galaxy's proven triple-fan cooler, which has been used on older Galaxy/KFA2 graphics cards. The cooler utilizes a long aluminum fin array, to which heat is conveyed by several copper heat pipes. It is then ventilated by three 90 mm LED-lit fans. Display outputs include one standard-sized DisplayPort, and three mini-DisplayPort connectors. According to OCUK, the KFA2 GTX 680 HOF Edition will start shipping on May 11.

MSI has received high marks from all quarters for its high-end gaming laptops, including being selected for Innovations Honorees at the CES 2012, the IT industry's equivalent of an Oscar. Now, MSI is introducing the GE60 and GE70-the ultimate in next generation gaming notebooks. They feature Intel's latest quad core processor and new generation NVIDIA GeForce GT 650M discrete graphics card. Specially designed to meet the extreme demands of extreme gamers around the world. These killer notebooks also boast awesome peripherals.

PowerColor launched its second Radeon HD 7750 graphics card, a Go! Green variant. Models of this series tend to be energy-efficient (with slightly lowered voltages, reducing power draw), while maintaining reference clock speeds. Another striking feature of Go! Green variants is their silent passive-heatsink that cools the GPU and VRM. To maintain high temperature tolerance, and energy-efficiency, PowerColor tends to employ high-grade voltage regulation components on their Go! Green cards. In case of this card, it is said to utilize PowerPAK SO-8 MOSFETs, shielded chokes, and conductive-polymer capacitors.

The card sticks to reference clock speeds of 800 MHz (core) and 1125 MHz / 4.50 GHz effective (memory), packs 512 Graphics CoreNext stream processors, and 1 GB of GDDR5 memory over a 128-bit wide memory interface. The cooler is similar to the one featured on previous-generation Go! Green cards from PowerColor, it consists of a dense aluminum fin heatsink, to which heat is conveyed by copper heat pipes that draw head directly off the core. Heat dissipation happens passively. Expect the card to charge a tiny premium over other Radeon HD 7750 cards in the market.

Over the weekend, MSI launched a factory-overclocked variant of its GeForce GTX 560 SE graphics card (model: N560GTX-SE-M2D1GD5/OC). Designed identical to the card MSI started its GTX 560 SE lineup with, the OC model features out of the box clock speeds of 750/1500/957(3828) MHz core/CUDA cores/memory(effective), against reference clock speeds of 736/1472/957(3828) MHz. The card packs a custom-design PCB that makes use of copperMOS, and a custom-design cooler that uses two fans to ventilate a large aluminum fin heatsink fed by copper heat pipes. The card features 288 CUDA cores, and 1 GB of GDDR5 memory across a 192-bit wide memory interface. Expect this card to cost under $200.

Soon after launching GeForce GTX 680 JetStream, Palit is working on its variant with double the amount of memory, at 4 GB. The GTX 680 JetStream 4 GB joins Gainward's GTX 680 Phantom 4 GB and Galaxy GTX 680 4 GB, at being some of the first cards with double the memory amount, which could just come handy with triple-monitor 3D Vision Surround setups.

Unlike the 2 GB GTX 680 JetStream, which has 1150 MHz (core boost) and 6.30 GHz (memory), the 4 GB variant sticks to NVIDIA reference clock speeds of 1056 MHz (core boost) and 6.00 GHz (memory). Like the 2 GB variant, the new card will use 6-pin and 8-pin PCIe power connectors to draw power. We can see from pictures that the PCB is a slight variation of NVIDIA's reference design, besides the GDDR5 memory chips on the reverse side of the PCB, which are not cooled by any back-plate. Its launch could be very soon.

We know from a late-March article that NVIDIA is working on two new SKUs based on its GK104 silicon, for launch in May. With the Kepler architecture, particularly with the design of the new-generation Streaming Multiprocessors (SMX), NVIDIA substantially increased CUDA core density. Each SMX holds 192 CUDA cores, and as with the previous-generation Fermi architecture, the SMX count is the only thing NVIDIA can tinker with, to control CUDA core count in new GPUs. GeForce GTX 680's little brother, hence will have 7 out of 8 SMX units enabled, and end up with a CUDA core count of 1344. This leaves easier to configure parameters such as clock speeds, for NVIDIA to design the perfect SKU to capture a price-point. NVIDIA is targeting the sub-$399 market, while somehow maintaining competitiveness with Radeon HD 7950.Specifications of the new SKU follow.

When we saw glimpses of Sapphire Radeon HD 7970 Toxic 6 GB graphics card, we knew Sapphire was prioritizing on aesthetics a lot. That turns out to be the case, as the first pictures of this monstrosity reveal. The PCB and cooler are designed from scratch, by Sapphire. The PCB accommodates 6 GB of memory in 24 GDDR5 memory chips, 12 on each side. To power the factory-overclocked 28 nm "Tahiti" GPU and 24 GDDR5 7 GT/s memory chips takes some really strong VRM. Sapphire implemented an 8+3 phase power supply, that makes use of solid-state chokes (don't whine under stress), and International Rectifier DirectFETs. The VRM draws power from two 8-pin PCIe power connectors.More details, and a benchmark follow.

Palit Microsystems Ltd, the leading graphics card manufacturer, announced a brand new Jetstream series at the GeForce GTX 680 The Palit Jetstream series of graphics cards features innovative cooling and an optimized product design to deliver gamers the ultimate gaming experience. As the latest and most powerful GPU in the series, the Palit Jetstream GeForce GTX 680 Jetstream guarantees gamers cutting-edge performance and an explosive new gaming experience.

The factory overclocked Palit GeForce GTX 680 Jetstream is at boost clock 1150 MHz that is +92 MHz than the standard speed and 2GB GDDR5 memory clock is set at 6300 MHz (+292 MHz higher). Equipped with the Jetstream cooler and optimized product design, Palit GeForce GTX680 Jetstream performs 12.5% higher at 3DMark11 Xscore and average 10% higher among all hot gaming titles.

ZOTAC is flexing its engineering muscle. First, it was talk of a 2 GHz GeForce GTX 680 by one of its senior executives, and now this, ZOTAC GeForce GTX 680 Extreme Edition. Pictured below, the card's design is reminiscent of the crazy engineering endeavors ZOTAC China undertakes, to come up with some extremely powerful designs, which seldom get out of the APAC region (to EMEAI and NA regions).

ZOTAC took a top-tier binned GK104 GPU, 2 GB of high-grade Hynix GDDR5 memory chips, and paired them with a 12-phase VRM power supply. Apart from bleeding-edge International Rectifier GaNpowIR driver-MOSFETs, the VRM uses server-grade tantalum capacitors, and FPCAP multi-phase capacitors. To drive it all, ZOTAC used CHiL CHL8318 VRM controller.

In anticipation of the official launch, PowerColor has served up a fresh batch of pictures depicting its Radeon HD 7970 Vortex II Edition graphics card. Besides providing fresh photos, PowerColor has also confirmed that this new Tahiti-powered card will have its GPU set to 1100 MHz (up from the stock 925 MHz) and the 3 GB of on-board GDDR5 memory clocked at 5700 MHz (5500 MHz stock).

In addition to higher clocks, the HD7970 Vortex II features a dual-slot cooler with two fans (allowing for a little airflow adjustment) and three heatpipes, a backplate to speed up heat dissipation, 2048 Stream Processors, a 384-bit memory interface, a PCI Express 3.0 x16 bus interface, CrossFireX and Eyefinity support, and five display outputs (DVI x 2, HDMI x 1, mini DisplayPort x 2).

The HD7970 Vortex II Edition is expected to become available next month. Its price tag is still unknown.

MSI is working on a factory-overclocked GeForce GTX 680 graphics card, which was briefly put up on its German website, before being pulled, suggesting that the company is not entirely ready with it. Carrying the model number N680GTX-PM2D2GD5/OC, the card features NVIDIA-reference board design. It features out of the box overclocked core speeds of 1056 MHz (base core), 1111 MHz (boost core), vs. reference speeds of 1006 MHz (base core), 1058 MHz (boost core). The memory clock is unchanged, at 6.00 GHz (GDDR5 effective).Update: Sources among retail channels told us that this particular model (N680GTX-PM2D2GD5/OC) was canned at the very last moment. It's possible, however, that the 1056(core)/1111(boost) MHz clock profile could be carried over to future non-reference design models, such as the Twin Frozr IV.

Galaxy is working on a new GeForce GTX 680 graphics card. Pictures below reveal the Galaxy GTX 680 4 GB. As the name suggests, it is a non-reference design that's based on doubling the memory amount. The card features an out-of-the-box core OC of 1.10 GHz (base, boost not mentioned).

It did this, by using sixteen 2 Gbit GDDR5 memory chips. There's more to this card than its memory amount. The PCB is designed from scratch, and uses a strong 5+2 phase VRM, which draws power from 6+8 pin power connectors. The VRM appears to make use of International Rectifier-made DirectFETs. Perhaps Galaxy also went off-spec with the VRM controller, and maybe it supports a software interface. The cooler is an in-house design by Galaxy, too. It consists of a large heat-pipe fed aluminum fin array, ventilated by two 90 mm fans.

GIGABYTE took its own sweet time launching its GeForce GTX 680, but no harm done. Carrying the product code GV-N680D5-2GD-B, GIGABYTE's graphics card sticks to NVIDIA reference board design, decorated with a slick-looking abstract art. The card also sticks to NVIDIA reference clock speeds of 1006 MHz (core), 1058 MHz (boost), and 1502 MHz / 6.00 GHz effective GDDR5 memory. It is armed with 2 GB of memory sitting across a 256-bit wide memory interface. Based on the 28 nm GK104 GPU, NVIDIA GeForce GTX 680 is powered by 1536 CUDA cores, and a revolutionary, energy-efficient architecture. GIGABYTE GeForce GTX 680 is priced at US $499.

It looks like murmurs about the $499 (excl. taxes) price-tag of GeForce GTX 680 have more than an element of truth in them, after all. European retailer PC Components listed an MSI-branded GeForce GTX 680 graphics card (model: N680GTX-PM2D2GD5) for 492€ (including VAT), and 416.95€ (excluding VAT). This reinforces the theory of a US $499 (excluding taxes) price-tag (including taxes price varies significantly between states and other US territories).

The listing also reveals the box-art of MSI's card, and various other features of the GeForce GTX 680, such as NVIDIA GPU Boost Technology, NVIDIA 3D Vision Surround (with the ability to connect all three displays to a single graphics card), clock speeds of 1006 MHz (core) 1056 MHz (boost), 1502 MHz (6.00 GHz GDDR5 effective memory), 2 GB memory, and 195W TDP.Find the listing here.

Even as launch of the GK104-based GeForce GTX 680 nears, it's clear that it is emerging that it is not the fastest graphics processor in the GeForce Kepler family, if you sift through the specifications of the GK110 (yes, 110, not 100). Apparently, since GK104 meets or even exceeds the performance expectations of NVIDIA, the large-monolithic chip planned for this series, is likely codenamed GK110, and it's possible that it could get a GeForce GTX 700 series label.

3DCenter.org approximated the die size of the GK110 to be around 550 mm², 87% larger than that of the GK104. Since the chip is based on the 28 nm fab process, this also translates to a large increment in transistor count, up to 6 billion. The shader compute power is up by just around 30%, because the CUDA core count isn't a large increment (2000~2500 cores). The SMX (streaming multiprocessor 10) design could also face some changes. NVIDIA could prioritize beefing up other components than the CUDA cores, which could result in things such as a 512-bit wide GDDR5 memory interface. The maximum power consumption is estimated to be around 250~300 Watts. Its launch cannot be expected before August, 2012.

If you thought MSI made too much song and dance about the product design of its R7970 Lightning, particularly the GPU Reactor module, think again. When augmented with liquid nitrogen cooling, the card has the electrical muscle required to sustain 1.7V, and facilitate a staggering 1800 MHz core clock speed, with 1925 MHz memory (7.70 GHz GDDR5 effective), churning out a gargantuan memory bandwidth of close to 370 GB/s, all thanks to the genius of Swedish proverclocker Elmor.

This R7970 Lightning on 'roid-rage was stable enough to bag a 3DMark 11 (performance preset) score of P15035 points. The rest of the test-bed consisted of an Intel Core i7-3960X Extreme Edition six-core chip clocked at 5207 MHz, with 4 GB (4x 1 GB) DDR3 memory clocked at 2314 MHz, and MSI Big Bang XPower II motherboard, to seat it all. Perhaps this is an indication that AMD Radeon HD 7900 can work wonders on potent non-reference designs, such as MSI's R7970 Lightning.

Closely trailing the launch of NVIDIA's GeForce GTX 680, and keeping up with its own streak of launching a new graphics card line each month since January, AMD will unveil its Radeon HD 7990 graphics card in April, or so it's reported. INPAI reports the clock-speed and chip-configuration of the upcoming dual-GPU monstrosity. The Radeon HD 7990 packs two 28 nm "Tahiti" GPUs as a "Crossfire on a stick" solution. The Tahiti chips will be clocked at 850 MHz (core), and 1250 MHz (5.00 GHz effective) memory.

The chip-configuration of each of the two Tahiti chips will be the same as that on the Radeon HD 7970, with 2048 Graphics CoreNext stream processors, 128 TMUs, 32 ROPs, and 384-bit wide GDDR5 memory interface, holding 3 GB of memory, each. The total memory on the card will hence be 6 GB. With the Radeon HD 7970 refusing to budge from its US $549 price-point, it's quite natural that the Radeon HD 7990 will be priced very high. It is gunning to retain the performance crown that's currently disputed between the Radeon HD 6990 and GeForce GTX 590.

AMD today reached a major milestone in the graphics industry with worldwide availability of its full line of next generation AMD Radeon HD 7000 Series GPUs in less than three months. Starting in December, AMD launched the AMD Radeon HD 7900 Series, followed in February by the AMD Radeon HD 7700 Series and completed today with availability of the AMD Radeon HD 7800 Series graphics cards.

"Bringing the first 28nm graphics cards to market in December spurred us to continue pushing the boundaries, product after product, culminating with today's product availability," said Zvika Greenstein, director of product management, GPU Division, AMD. "Look at our feature set: Graphics Core Next, AMD Eyefinity 2.0, AMD PowerTune, AMD ZeroCore Power technologies and of course our GHz Edition graphics cards - it is without doubt that AMD stands alone in the graphics industry."

GIGABYTE Technology Co. LTD., a leading manufacturer of motherboards and graphics cards, is pleased to present Radeon HD 7800 Overclock Series Graphics Card: GV-R787OC-2GD, GV-R785OC-2GD. Built with AMD's latest 28nm GPU and GDDR5 memory, GIGABYTE makes these cards with higher core clock. Equipped with GIGABYTE's latest in-house cooling design and adapted with GIGABYTE Ultra Durable materials, GIGABYTE makes sure that Radeon HD 7800 Series is with the best speed of heat dissipation and performance.

GIGABYTE Radeon HD 7800 Series also provides a number of innovative features including the latest AMD APP Acceleration, Microsoft DirectX 11 supported, AMDHD3D, Crossfire, and PCI-Express 3.0 supported. GIGABYTE GV-R787OC-2GD, GV-R785OC-2GD, guarantee gamers to have the best gaming experience with realistic visuals and fantastic gaming performance.

Colorful is well-known for its highly innovative graphics card designs, it is one of China's leading graphics card brands. Some of its graphics card designs have captured our imagination. Its latest creation is a DIY mini-ITX barebones system for gaming, called Desert Eagle. The package consists of Colorful's own-design slim-form-factor (SFF) chassis, which bears a swanky combination of red and black, with ample perforations and and top handles; a custom-design, low-profile Colorfire AMD Radeon HD 6750 graphics card (Colorfire is Colorful's Radeon-selling brand); a mini-ITX socket LGA1155 motherboard based on the Intel H67 chipset (model: i-H67HD U3); and a 300W PSU.

Here's a picture of Toshiba's its newest gaming notebook in the works, the Qosmio X870. Although unveiled, it will be a little while before we can see this 17.3-incher in stores. That's because it's said to powered by "next-generation" Core processors (Ivy Bridge), and "next-generation" NVIDIA GeForce GPU (Kepler), with 3 GB of GDDR5 memory. Its 17.3-inch TruBrite display packs 1920x1080 pixels resolution. Other notable specifications of this brute includes 2TB SSD+HDD hybrid, Bluetooth 4.0, four USB 3.0 ports, Harman-Kardon speakers, Blu-ray drive, and wired Ethernet. According to the source, the Qosmio X870 is headed for a Q2-2012 launch.