NVIDIA announced its new entry-level GeForce GT 730 graphics processor. Based on the same 28 nm "GK107" silicon as the GeForce GT 740, which launched last month, the GT 730 is essentially a GT 740 with lower clock speeds, and slower DDR3 memory. Core clock speeds start at 908 MHz, and memory at 1.80 GHz (DDR). 1 GB is the standard memory amount. Most cards based on this chip will be based on half-height (low-profile) PCBs, some single-slot with active (fan) cooling, others double-slot, with passive (fan-less) cooling. In the era of AMD GCN-based APUs, and Intel Iris Pro graphics, NVIDIA could be targeting a dwindling two-figure price.

ASUS launched a trio of GeForce GT 740 graphics cards, the GT740-2GD3, which sticks to reference clock speeds of 933 MHz core and 1750 MHz (DDR), featuring 2 GB of DDR3 memory; the GT740-1GD5, featuring factory-overclocked speeds of 1053 MHz, and an untouched 5.00 GHz GDDR5 memory clock; and its 2 GB variant, the GT740-2GD5. Based on the 28 nm GK107 silicon, the GeForce GT 740 offers 384 CUDA cores 32 TMUs, 16 ROPs, and a 128-bit wide memory interface. It's NVIDIA's bid to capture the sub-$100 market.

Galaxy launched one of the first few factory-overclocked, low-profile GeForce GT 740 graphics cards, the Galaxy GT 740 OC Slim 2GB. The card relies entirely on the PCI-Express 3.0 x16 bus for power, and features an aluminium fan-heatsink that, sadly, is thicker than one slot. The card offers a slight factory OC of 1058 MHz core (vs. 1006 MHz reference), while leaving the memory untouched at 5.00 GHz (GDDR5 effective). Based on the 28 nm GK107 silicon, the GT 740 offers 384 CUDA cores, 32 TMUs, 16 ROPs, and features a 128-bit wide GDDR5 memory interface. Galaxy's card offers a dual-link DVI, an HDMI 1.4a, and D-Sub. Low-profile brackets are included.

NVIDIA announced its entry-level graphics card offering for the 700 series, the GeForce GTX 740. A rebadge of the GT 640, the card is based on the GK107 GPU, based on the "Kepler" micro-architecture. It features 384 CUDA cores, 32 TMUs, and 16 ROPs. Also featured is a 128-bit wide GDDR5 memory interface, holding 1 GB of memory. 2 GB variants will also be available. The card has a TDP of just 64W, and should make do with slot-supplied power, although some variants with 2 GB or factory overclocks, should feature a 6-pin PCIe power input. NVIDIA hopes to capture the sub-$100 market with this card. It faces competition from integrated solutions such as AMD A-Series APUs, and Intel Iris Pro 5000 series.

Here are some of the first pictures of an Inno3D branded GeForce GT 740 graphics card, the GT 740 iChill. Based on a custom-design PCB, the card features a strong VRM (by GK107 requirements), which draws power from a 6-pin PCIe power connector. It features 1 GB of GDDR5 memory, across a 128-bit wide memory interface. Confirming that the GT 740 is based on the GK107, the marketing poster leaked to the web reads its ASIC string to be "GK107-425." It's configured with 384 CUDA cores, 32 TMUs, and 16 ROPs. The GPU is clocked at 1100 MHz (a factory-overclock), while the memory runs at 5.20 GHz (GDDR5-effective).

Cooling the 65W TDP GPU is a similarly overkill iChill HerculeZ 2000 cooler, designed in-house by Inno3D, which uses a dense aluminium fin-stack, to which heat drawn from the GPU, is fed by a pair of 8 mm-thick copper heat pipes, and ventilated by a pair of 100 mm fans. The cooler shroud on which the fans are suspended, can be detached, by simply removing six thumb-screws, letting you clean the heatsink underneath, which has been a USP of Inno3D's cooling solutions. Inno3D also put out its own performance numbers for the card, in which it claims the GT 740 iChill to be faster than previous generation GTX 650 (they're both based on the same chip).Performance graphs follow.

NVIDIA is planning to drag its entry-level GPU lineup through 2014 with the 'new' GeForce GT 740. Reports suggest that the card is a re-branding of the 28 nm GK107-based GeForce GT 640, with higher clock speeds. The chip will feature 384 CUDA cores, 32 TMUs, 16 ROPs, and a 128-bit wide GDDR5 memory interface, holding 1 GB of memory. Variants with 2 GB of memory will also be available. The card draws all its power from its PCI-Express 3.0 x16 bus interface, however some custom-designs could feature single 6-pin power connectors. NVIDIA AIC partners will have their custom-design cards out on day-one. Expreview revealed pictures of two such cards, by Galaxy and Gainward.

Gigabyte expanded its GeForce GTX 650 graphics card lineup with two new models featuring its 100 mm fan-heatsink, the GV-N650D5-1GI (1 GB) and GV-N650D5-2GI
(2 GB). The cards feature non-reference design Ultra Durable 2 PCBs, and chunky aluminum heatsinks with copper cores, which are ventilated by 100 mm fans. The card features 1 GB or 2 GB of GDDR5 memory across a 128-bit wide memory interface. Based on the 28 nm GK107 GPU, the GeForce GTX 650 features 384 CUDA cores. The card features NVIDIA reference clock speeds of 1058 MHz core, with 5.00 GHz memory. It draws power from a 6-pin PCIe power connector. Display outputs include one each of dual-link DVI, HDMI (gold-plated connector), and D-Sub (VGA). The 1 GB model is expected to be priced around $100, and the 2 GB around $130.

Colorful unveiled a new GeForce GT 640, the GT 640 PRO X4. Just as the name, the graphics solution delivers a reliable platform to ensure a stable business environment and to meet the needs of four displays connectivity. The display connectivity options include two DMS59 ports, and cables are provided that convert each DMS59 to two DVI-I single-link, which supports digital resolutions of up to 1920 x 1200 pixels. And each of the DMS59 ports uses EMI shield for reducing the noise signals.

The card is based on single slot, full height and fan cooler design. The clock is the same as the reference card, the core runs at 900 MHz, and the GDDR3 memory runs at 1782 MHz. The GT 640 PRO X4 uses NVIDIA GK107 with 28 nm architecture, and the TDP is only 65W. Unlike the low-end multi-display solutions, the Colorful GT 640 PRO X4 has 384 CUDA cores and 2G memory to meet the need of large resolution. Pricing information is not released.

Evidently, buyers still fall for the old memory amount trick when choosing graphics cards, and Club 3D isn't late to capitalize on that. The company released a new GeForce GT 640 low-profile double-slot graphics card that crams in 4 GB of GDDR3 memory. Its GPU is clocked at 900 MHz, and memory at 1600 MHz. The 4 GB memory is spread across a 128-bit wide interface. Display outputs include dual-link DVI, HDMI, and D-Sub. Based on the 28 nm GK107 GPU, the GeForce GT 640 packs 384 CUDA cores. Here's the kicker - it is priced at 177€.

Leadtek Research Inc, a world-leading maker of professional gaming graphics cards, launches the overclocking version of the GeForce GTX 650 graphics card. The new-generation GeForce GTX 650 is based on the new 28nm GK107 ASIC derived from the NVIDIA Kepler architecture. With graphics that clock up to 1,100MHz, the GeForce GTX 650 OC comes in a dual-fan design with 1GB GDDR5 memory and four outputs onboard to support output for up to four monitors for gamers to enjoy live experience at the most best price. There is also a standard version with 2GB GDDR5 memory.

SPARKLE, one of the leading manufacturers of graphics solutions launches two new products - SPARKLE GTX650 OC Dragon Cyclone & SPARKLE GTX650 OC. The latest series features a 384 CUDA cores packed GPU, 128Bit 1024MB GDDR5 memory, and both tweaked with above reference core clocks for OC Dragon Cyclone & OC edition to meet all user requirements.

A member of the Kepler GK107 family, the SPARKLE GTX 650 OC Dragon Cyclone & SPARKLE GTX 650 OC provides the BEST performance to price ratio in its category. SPARKLE R&D team have utilized the new SPARKLE GTX650 GPU to allow for maximum performance, allowing it too boost graphics system performance. The latest series allows support for the latest technology to improve multimedia performance and HD entertainment like Microsoft DirectX 11, NVIDIA PhysX, NVIDIA CUDA. Utilizing NVIDIA surround gamers can easily build a three monitors system without Display Port output.

Here are the first pictures (one a CGI drawing, the other extremely grainy) of Palit GeForce GTX 660 OC Edition and GeForce GTX 650. The GeForce GTX 660 OC Edition appears to feature an aluminum fin stack design, with the same TurboFan Blade 90 mm fan featured on GeForce GTX 660 Ti, GTX 670, and GTX 680 JetStream graphics cards. For a change, we see Palit ditch orange and gold for a blue+black color scheme. Not much else is revealed about the card on the box. The GTX 650, on the other hand, appears to be using a simple fan-heatsink to cool the GK107 GPU. The two cards are due for a little later this week.

According to a new 3DCenter.org report, NVIDIA is planning a joint launch of two its key mid-range GPUs, the GeForce GTX 660 and GeForce GTX 650, on September 12, 2012. The two GPUs will let NVIDIA capture key sub-$300 and sub-$200 price-points, with performance levels that could destabilize AMD's Radeon HD 7800 and HD 7700 series. Based on the GK106 silicon, the GTX 660 is said to pack 960 CUDA cores and 2 GB of GDDR5 memory across a 192-bit wide memory interface; while the GK107-based GeForce GTX 650 is said to pack 384 CUDA cores and 1 GB of GDDR5 memory across a 128-bit wide memory interface.

Here is the first picture of what the retail version of NVIDIA's GeForce GTX 650 graphics card looks like. Based on the same GK107 silicon as the GeForce GT 640, the GTX 650 features faster GDDR5 memory. Its reference design board closely resembles that of the GT 640, with the exception of the black PCB and a 6-pin PCIe power connector to draw power from. Interestingly, the new chip has the same typical power draw rating as the GT 640, at 65W. This could give it a significant performance/Watt edge over its predecessor, the GeForce GTS 450. The GeForce GTX 650 packs 384 CUDA cores, 16 ROPs, and a 128-bit wide GDDR5 memory interface, holding 1 GB of memory. It is said to feature similar GPU clock speed to the GT 640, lack of GPU Boost, but with 5.00 GHz GDDR5 memory, compared to the 1800 MHz GDDR3 memory the GT 640 features. The GTX 650 is bound for a little later this quarter.

AFOX Corporation, a professional and leading manufacturer of Graphics Cards, today announced to release the latest AFOX Geforce GT 640 Graphics Card AF640-2048D3L1 - the newest model designed for mainstream users with excellent 3D display and gaming performance, perfect low profile size to all PC types, full PCI Express 3.0 and DirectX11 support.

Compared to the previous generation, the new AFOX AF640-2048D3L1 based on latest NVIDIA's 28nm Kepler GK107 GPU, has up to 25% better performance than the old GTS 450. The AFOX GT 640 Graphics Card has 384 Cuda Cores, an impressive 900MHz core speed, 2048MB of DDR3 memory running at 1782MHz and 128-bit memory interface. It supports NVIDIA CUDA, PhysX and Blu-Ray 3D technology, which are designed for both high quality gaming and great home theater solutions. Without any additional power requirement, the testing result shows that the new AFOX GT 640 Graphics Card has an unbeatable performance/Watt ratio compared with previous generation products.

EVGA kicked off its GeForce GT 640 lineup with two models, a double-slot one (model: 02G-P4-2643-KR), and a single-slot (model: 02G-P4-2645-KR), both of which are priced at US $109.99. The GeForce GT 640 is based on the new 28 nm GK107 silicon, with 384 CUDA cores, and a 128-bit wide GDDR5 memory interface. The cards rely entirely on the PCI-Express slot for power, and support PCI-Express 3.0 x16 interface. Both models provide the same display output load-out, including two dual-link DVI and a mini-HDMI. The cards should be available right away.

TechPowerUp today announced GPU-Z 0.6.1, and with it, a new graphics card giveaway in partnership with PowerColor, in which you could win some of the fastest and coolest Radeon HD 7000 series graphics cards in the industry. Version 0.6.1 of GPU-Z adds support for some new GPUs on the horizon, such as NVIDIA GeForce GTX 690, GeForce GTX 670, GeForce GT 640 (desktop), GeForce GT 630, GeForce 605, GeForce GTX 675M (mobile), and GeForce GTX 670M; AMD Radeon HD 7970M (mobile), and Radeon HD 7450 (desktop); Intel HD 4000 and HD 2500 "Ivy Bridge". GPU-Z 0.6.1 improves NVIDIA GPU Boost clock speed detection. A host of other stability and reliability changes were made (refer to the change-log below).

With GPU-Z 0.6.1, TechPowerUp is teaming up with PowerColor to present to you this year's first GPU-Z Giveaway, in which you could win some great graphics hardware. Up for grabs are PowerColor HD 7970 PCS+ Vortex II, PowerColor HD 7870 PCS+ Vortex II, and the yet-unannounced PowerColor HD 7770 PCS+ Vortex II. To participate in the Giveaway, simply run GPU-Z 0.6.1 (main version), click on the "PowerColor Giveaway" tab, and follow the instructions. Entries are open till June 01, 2012; multiple entries may lead to elimination. Good Luck!DOWNLOAD: TechPowerUp GPU-Z 0.6.1 | TechPowerUp GPU-Z 0.6.1 ASUS ROG Edition

The complete change-log follows.

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.

Following the launch of a couple of more GK104-based SKUs, namely GeForce GTX 670 Ti, and GeForce GTX 670, some time in May; NVIDIA will launch its third (after GK104 and GK107) Kepler architecture-based silicon, codenamed GK106. GK106 will make up sub-$200 SKUs, and succeeds the GF116, on which SKUs such as the GeForce GTX 550 Ti, are based. The GK106 will make up at least one known desktop SKU, called GeForce GTX 660.Its specifications are listed below.

NVIDIA's GeForce GTX 680 literally kicked the door open as it made its entry. We're learning of NVIDIA's plans to milk the GK104 chip by carving out two more SKUs: the GeForce GTX 670 Ti, and GTX 670. These two SKUs will let NVIDIA capture price points deep within the $400-499 and $300-399 ranges, to compete with AMD's Radeon HD 7950 and Radeon HD 7870. These two SKUs will be released in May. Around the May-June time-range, NVIDIA could also introduce the GTX 690, which we're hearing is a dual-GK104 graphics card that's designed to compete with Radeon HD 7990, which launches in April.

Also in May, NVIDIA will launch desktop discrete graphics card SKUs based on the GK107 chip, which makes up its GeForce GT 650M/640M mobile graphics SKUs. Following this, some time in Summer, NVIDIA will release a new chip, the GK106, which will make up the GeForce GTX 660, which will be out to compete with Radeon HD 7850, and HD 7700 series. It looks like NVIDIA is waiting on current inventories of GF114-based SKUs to get digested, including those of the recently-launched GeForce GTX 560 SE, and is hence in no hurry to launch a new GPU to capture the sub-$250 price-points. Besides the dual-GPU Radeon HD 7990, there's nothing new in the works, at the red camp that we know of.

The GeForce GTX 680 may be today's highlight release but it's not the only Kepler-based offering unveiled by NVIDIA. Besides announcing its new flagship desktop card, NVIDIA today also introduced multiple GeForce 600M Series mobile cards, four of which are powered by the 28 nm GK107 chip.

The Kepler-flavored models in the 600M family are the Enthusiast-grade GeForce GTX 660M and the 'Performance class' GT 650M, GT 640M and GT 640M LE.

NVIDIA seems to have scored big design wins with Acer, for its next-generation GPUs. First, we had reports of Acer's VA40 combining Intel "Ivy Bridge" Core processors with NVIDIA GeForce GT 640M, and now Acer Timeline M3-581TG, following the same path. The M3-581TG is a 15.6-inch Ultrabook (one of the first of its kind). Pictures of this model reveal case-badges of its key components, including an NVIDIA GEFORCE GT case-badge, which gives out GPU model (GeForce GT 640M) and memory amount (1 GB). This could very well be the way NVIDIA's GeForce GT family of GPUs will be designated in case-badges.

Based on the 28 nm GK107 silicon, the GeForce GT 640M packs 384 CUDA cores running at speeds of up to 625 MHz, with 405 MHz base clock, and 910 MHz DDR3 memory, churning up 28.8 GB/s memory bandwidth. Other notable components of the Timeline M3-581TG include Intel Core i7-2637M (1.7 GHz dual-core, 4 MB of L3 cache) processor, 4 GB DDR3-1333 memory, and 256 GB SSD.

Here are some key bits of information concerning the upcoming GeForce GTX 680, a performance single-GPU graphics card based on the 28 nm GK104 GPU by NVIDIA. The information, at face value, is credible, because we're hearing that a large contingent of the media that finds interest in the GPU industry, is attending the Game Developers Conference, where it could interact with NVIDIA, on the sidelines. The source, however, is citing people it spoke to at CeBIT.

First, and most interesting: with some models of the GeForce 600, NVIDIA will introduce a load-based clock speed-boost feature (think: Intel Turbo Boost), which steps up clock speeds of the graphics card when subjected to heavy loads. If there's a particularly stressing 3D scene for the GPU to render, it overclocks itself, and sees the scene through. This ensures higher minimum and average frame-rates.

NVIDIA's GeForce Kepler 107 (GK107) will go into making several of its entry-thru-mainstream SKUs, such as N13 GeForce M GPUs for notebooks, and N14 Quadro GPUs for professional graphics cards, but more importantly, it will also go into making the D14 GeForce 600 series discrete PC graphics cards for the retail and OEM markets. A CGI sketch of the reference design board was leaked to the web, which found its way to VR-Zone, which reports that the GK107 will be used in two desktop PC discrete graphics SKUs: D14M2-20, and D14P1-10, based on the GK107-200 (512 MB DDR3) and GK107-300 (GDDR3/GDDR5) variants of the chip, respectively.

The sketched GK107 graphics card appears to be similar to the GF108-based GeForce GT 440 board. The GPU will feature a 128-bit wide DDR3/GDDR3/GDDR5 memory interface. Its cooler design is similar, with a 11-blade axial fan, and a heatsink with spirally-projecting aluminum fins. Apparantly legacy D-Sub support will be dropped for the first DVI-I connector. There will be two dual-link DVI connectors, and a mini-HDMI.

2012-13 promises to be a period of big graphics product launches, centric to a new DirectX version, DirectX 11.1, which will ship with Microsoft's next major Windows version (currently referred to as Windows 8). Information compiled by ExpertsPC.com and 4Gamer.net tables what NVIDIA's next-generation graphics family could look like, and around what time it could be released to market. With its next-generation GeForce Kepler family of GPUs, NVIDIA will follow a sensible bottom-up product release model, to ensure that it isn't met with any technical hurdles with TSMC's new 28 nm manufacturing process, and so it could launch GPUs with increasingly higher transistor counts, till its top-of-the-line GPU is outed.

The first GPU in NVIDIA's pipeline is the GeForce Kepler 107 (GK107), on which will be based entry thru lower-mainstream SKUs. The data doesn't reveal things like core counts, but points out that GK107 will have a 128-bit wide GDDR5 memory interface, will use the current-generation PCI-Express 2.0 bus, will be built on the 28 nm process, and will support DirectX 11.1. This will be followed by the GK106, on which "sweet-spot" SKUs could be based. This will be NVIDIA's first PCI-Express 3.0 compliant GPU, it will have a 256-bit wide GDDR5 memory interface.