NVIDIA has begun selling its compact RTX 4000 Ada Lovelace graphics card, offering GeForce RTX 3070-like performance at a mere 70 W power consumption, allowing it to fit in almost all desktop PCs. The low-profile, dual-slot board is priced higher than the RTX 4080 as it targets professional users, but it can still be used in a regular gaming computer. PNY's RTX 4000 Ada generation graphics card is the first to reach consumer shelves, currently available for $1,444 at ShopBLT, a retailer known for obtaining hardware before its competitors. The card comes with four Mini-DisplayPort connectors, so an additional mDP-DP or mDP-HDMI adapter must be factored into the cost.

The NVIDIA RTX 4000 SFF Ada generation board features an AD104 GPU with 6,144 CUDA cores, 20 GB of GDDR6 ECC memory, and a 160-bit interface. With a fixed boost frequency floating around 1560 MHz to reduce overall board power consumption, the GPU is rated for just 70 Watts of power. To emphasize the efficiency, this card requires no external PCIe power connector, as all the juice is fed through the PCIe slot. The GA104 graphics processor in this configuration delivers a peak FP32 performance of 19.2 TFLOPS, comparable to the GeForce RTX 3070. The 20 GB of memory makes the card more valuable for professionals and AI researchers needing compact solutions. Although the card's performance is overshadowed by the recently launched GeForce RTX 4070, the RTX 4000 SFF Ada's professional drivers, support for professional software ISVs, and additional features make it a strong contender in the semi-professional market. Availability and pricing are expected to improve in the coming weeks as the card becomes more widely accessible.More images, along with specification table, follow.

NVIDIA is preparing yet another variant of the GeForce RTX 3060 "Ampere" graphics card, by carving it out of the much larger "GA104" silicon. This SKU will feature 12 GB of faster 19 Gbps GDDR6X memory. Across a 192-bit memory bus, this yields an impressive 456 GB/s of memory bandwidth that's higher than the bandwidth of the original RTX 3070 with 14 Gbps GDDR6 memory across a 256-bit memory bus (448 GB/s). From what we can tell, the core-configuration of the card remains the same, with 3,584 CUDA cores, 112 Tensor cores, 28 RT cores, 112 TMUs, and 48 ROPs. This SKU is carved out of the GA104 silicon by enabling 28 out of 48 SM (that's 58% of the available number-crunching machinery); and slashing down the memory interface by 25%.

NVIDIA recently updated its product stack with an 8 GB 128-bit GDDR6 variant of the GeForce RTX 3060 (originally 12 GB 192-bit GDDR6), and the RTX 3060 Ti with faster 19 Gbps 256-bit GDDR6X memory (originally 14 Gbps 256-bit GDDR6). We're getting to learn that the new RTX 3060 Ti GDDR6X variant is designed to replace the older GDDR6 variant. NVIDIA's add-in card (AIC) partners are reportedly winding down orders of the original RTX 3060 Ti in favor of the newer GDDR6X variant. Perhaps the most striking aspect of the GDDR6X variant isn't that its memory bandwidth is 35% higher than that of the original RTX 3060 Ti; but that it sells at the same price.

The new GeForce RTX 3060 Ti GDDR6X is based on the 8 nm "GA104" silicon, and has the same core-configuration as the original RTX 3060 Ti, with 4,864 CUDA cores, 152 Tensor cores, 38 RT cores, 152 TMUs, and 80 ROPs; the same GPU boost frequency of 1665 MHz, and interestingly, the same typical board power of 200 W. What's changed is the switch to 19 Gbps GDDR6X memory compared to the original's 14 Gbps GDDR6, which results in a memory bandwidth of 608 GB/s, compared to the original's 448 GB/s.

NVIDIA manufactured a heap of large "GA102" Ampere silicon to cater to demand from the crypto-mining boom; only to see that demand vanish. With next-gen RTX 40-series awaiting ramp; the company has to digest these GA102 chips somehow, and is apparently letting its partners use them on performance-segment SKUs such as the GeForce RTX 3070 Ti. The RTX 3070 Ti is normally based on the GA104 silicon, which it maxes out, enabling all 6,144 CUDA cores, 48 RT cores, 192 Tensor cores, 192 TMUs, and 96 ROPs, besides the chip's full 256-bit wide GDDR6X memory interface. This SKU is now being carved out on the larger GA102, by enabling 48 out of 84 streaming multiprocessors (just 57% of the CUDA cores enabled); and narrowing the memory bus from its normal 384-bit, down to 256-bit.

The memory size remains at 8 GB, memory type at GDDR6X, and memory speed at 19 Gbps, working out to 608 GB/s of bandwidth. The most interesting aspect of carving the RTX 3070 Ti out of the GA102 has to be board power; with a ZOTAC-branded card listing it at 320 W, higher than the 290 W of GA104-based cards from the company. Sadly, this is a China-only SKU. Every custom-design graphics card, especially from a reputed AIC such as ZOTAC, has to go through qualification with NVIDIA; which means NVIDIA is not only aware of GA102-based RTX 3070 Ti cards, but is behind fusing the SMs to carve out the SKU, and developing the video BIOS and driver support. ZOTAC is kind enough to list the ASIC code on its website, and for this SKU it is "GA102-150-xx."

Some interesting technical specifications of the elusive two GPUs behind the Intel Arc "Alchemist" series surfaced. The larger DG2-512 silicon in particular, which forms the base for the Arc 5 and Arc 7 series, is interesting, in that it is larger in every way than the performance-segment ASICs from both NVIDIA and AMD. The table below compares the physical specs of the DG2-512, with the NVIDIA GA104, and the AMD Navi 22. This segment of GPUs has fairly powerful use-cases, including native 1440p gameplay, or playing at 4K with a performance enhancement—something Intel has, in the form of the XeSS.

The DG2-512 is built on the 6 nm TSMC N6 foundry node, the most advanced node among the three GPUs in this class. It has the highest transistor density of 53.4 mTr/mm², and the largest die-area of 406 mm², and the highest transistor-count of 21.7 billion. The Xe-HPG graphics architecture is designed for full DirectX 12 Ultimate feature support, and the DG2-512 dedicated hardware for ray tracing, as well as AI acceleration. The Arc A770M is the fastest product based on this silicon, however, it is a mobile GPU with aggressive power-management characteristic to the form-factor it serves. Here, the DG2-512 has an FP32 throughput of 13.5 TFLOPs, compared to 13.2 TFLOPs of the Navi 22 on the Radeon RX 6700 XT desktop graphics card, and the 21.7 TFLOPs of the GA104 that's maxed out on the GeForce RTX 3070 Ti desktop graphics card.

The deluge of NVIDIA leaks continue following the major cyber-attack on the company, with hackers getting away with sensitive information about current and upcoming products. The latest in this series covers the memory bus widths of the next-generation RTX 40-series GPUs based on the "Ada Lovelace" graphics architecture. There is early-information covering the streaming multiprocessor (SM) counts of each GPU, and their large on-die caches.

The top-of-the-line AD102 silicon allegedly has a 384-bit wide memory bus, similar to its predecessor. The next-best AD103 silicon has a 256-bit wide memory bus. Things get very interesting with the AD104, which has a 192-bit wide memory bus. The AD104 is a revelation here, because it succeeds a long line of NVIDIA GPUs with 256-bit memory buses (eg: GA104, TU104, GP104, GM204, etc). This confirms the theory that much like AMD, NVIDIA is narrowing the memory bus widths in the lower segments to cut board costs, and compensate for the narrower bus-width with large on-die caches, high memory data-rates, and other memory-management optimizations.

A few days ago, we found out that NVIDIA corporation has been hacked and that attackers managed to steal around 1 TB of sensitive data from the company. This includes various kinds of files like GPU driver and GPU firmware source codes and something a bit more interesting. The LAPSUS$ hacking group responsible for the attack is now threatening to "help mining and gaming community" by releasing a bypass solution for the Lite Hash Rate (LHR) GPU hash rate limiter. As the group notes, the full LHR V2 workaround for anything between GA102-GA104 is on sale and is ready for further spreading.

Additionally, the hacking group is making blackmailing claims that the company should remove the LHR from its software or share details of the "hw folder," presumably a hardware folder with various confidential schematics and hardware information. NVIDIA did not respond to these claims and had no official statement regarding the situation other than acknowledging that they are investigating an incident.Update 01:01 UTC: The hackers have released part of their files to the public. It's a 18.8 GB RAR file, which uncompresses to over 400,000 (!) files occupying 75 GB, it's mostly source code.

When NVIDIA announced the appearance of the GeForce RTX 3080 Ti mobile graphics card, we were left with a desire to see just what the GA103 silicon powering the GPU looks like. And thanks to the Chinese YouTuber Geekerwan, we have the first pictures of the GPU. Pictured below is GA103S/GA103M SKU with GN20-E8-A1 labeling. It features 58 SMs that make up for 7424 CUDA cores in total. The number of Tensor cores for this SKU is set to 232, while there are 58 RT cores. NVIDIA has decided to pair this GPU with a 256-bit memory bus and 16 GB GDDR6 memory.

As it turns out, the full GA103 silicon has a total of 7680 CUDA cores and a 320-bit memory bus, so this mobile version is a slightly cut-down variant. It sits perfectly between GA104 and GA102 SKUs, providing a significant improvement to the core count of GA104 silicon. Power consumption of the GA103 SKU for GeForce RTX 3080 Ti mobile is set to a variable 80-150 Watt range, which can be adjusted according to the system's cooling capacity. An interesting thing to point out is a die size of 496 mm², which is a quarter more significant compared to GA104, for a quarter higher number of CUDA cores.

NVIDIA has reportedly pushed midlife refreshes to its GeForce RTX 30-series "Ampere" graphics card family to beyond January, according to a report by Igor's Lab. The company was supposed to launch as many as three high-end graphics card SKUs in early-Q1, which include a 16 GB variant of the RTX 3070 Ti, which maxes out the GA104 silicon, a refreshed RTX 3080 12 GB variant, which keeps the CUDA core count of the original RTX 3080, but maxes out the 384-bit memory bus width of the GA102; and the RTX 3090 Ti, which maxes out both memory and CUDA cores on the GA102.

It's being reported that while the RTX 3090 Ti launch is on schedule, with announcements slated for NVIDIA's 2022 International CES presentation; the RTX 3070 Ti 16 GB and RTX 3080 12 GB could be launched only after the Chinese New Year (at least mid-February). The three SKUs, we predict, are designed to calibrate NVIDIA's lineup against a possible refresh of AMD's RDNA2 graphics architecture on the TSMC N6 (6 nm) node, which could allow the company to dial up engine clocks across the board, along with faster 18 Gbps GDDR6 memory, to better compete against the RTX 30-series. AMD is expected to announce these 6 nm GPUs in its CES presentation.

With the need for SLI compatibility out of the way, NVIDIA has been harvesting its larger GPUs to create lower-end SKUs to good effect, since the GeForce 10-series. Its latest such creation is select batches of GeForce RTX 3060 graphics cards sold through its AIC partners, which are based on the larger "GA104" silicon, over the "GA106" that it's natively based on. Nearly half of the 6,144 CUDA cores physically present on the chip are disabled to arrive at the 3,584-core count of the RTX 3060, besides a narrowing of the memory bus down to 192-bit. Since it is based on a different silicon, these RTX 3060 cards come with a different device-ID of "2487." The TechPowerUp GPU Database, which interoperates with the TechPowerUp GPU-Z Validation Database, localizes these oddball RTX 3060 cards to China.

Here are some of the first press-shots of the upcoming MSI GeForce RTX 3070 Ti SUPRIM X and MSI GeForce RTX 3070 Ti Ventus 3X graphics cards. Boxes of the cards confirm 8 GB GDDR6X as the memory configuration of the RTX 3070 Ti. Taking a close look at the press-shot of the RTX 3070 Ti SUPRIM X, and comparing it with those of the already-launched RTX 3070 SUPRIM X and RTX 3080 SUPRIM X, we find that the card looks closer to the RTX 3070 SUPRIM X. This would indicate that MSI is reusing the PCB and cooler design from that card, which means that the RTX 3070 Ti likely maxes out the GA104 silicon, rather than being a heavily cut-down GA102.

A maxed out GA104 would mean 6,144 CUDA cores spread across 48 streaming multiprocessors, 192 tensor cores, 48 RT cores, 192 TMUs, and 96 ROPs. The chip also features a 256-bit wide memory interface, which we now know is capable of handling fast GDDR6X memory. Besides significantly increased memory bandwidth, the RTX 3070 Ti could also dial up GPU clock-speeds. NVIDIA probably finds these changes sufficient to compete with the Radeon RX 6800, which outclasses the RTX 3070 in non-raytraced gaming.

GALAX today debuted a new line of GeForce RTX 3060 and RTX 3060 Ti graphics cards that come with NVIDIA's latest hash-rate limiter that make the cards unsuitable for crypto-currency mining. The cards look identical to the SKUs already launched by the company based on these GPUs, but are based on revised LHR (low hash-rate) versions of "GA104" or "GA106" ASICs that feature the hash-rate limiter. The oldest (launch) drivers for the RTX 3060 or RTX 3060 Ti won't work with these cards, you'll need the latest driver on the NVIDIA website. Today's announcements come in the wake of last week's introduction of the RTX 3070 and RTX 3080 LHR graphics cards by GALAX.

The NVIDIA RTX 3080 Ti and RTX 3070 Ti are set to be announced on May 31st after various delays. The two cards will then launch sometime in June with the review embargoes set as June 2nd for the RTX 3070 Ti and June 9th for the RTX 3080 Ti. The RTX 3070 Ti features the GA104-400 GPU 6144 CUDA cores and 8 GB GDDR6X memory. The RTX 3080 Ti will use the GA102-225 and include 10240 CUDA cores paired with 12 GB GDDR6X memory, We have already seen some retailers list custom RTX 3080 Ti cards from Gigabyte and MSI with prices ranging from 1338 USD to 2257 USD however these are likely placeholder values. The cards should be officially available to purchase sometime after the review embargoes lift in June.

Some time ago, NVIDIA introduced its GeForce RTX 3060 graphics card with GA106-300 Ampere GPU SKU. The GPU was the first to feature NVIDIA's latest additions like Resizable BAR and crypto mining algorithm limiter that limited the performance of the card while mining. However, despite NVIDIA's intention to keep the card out of the hands of crypto miners, there has been a lot of flaws in the plan. A lot of people discovered that the card still managed to turn in profits with the limiter enables. Later, NVIDIA accidentally released a driver that actually removes the limiter and enables the GPU to mine at full capacity, making the company's efforts useless.

Today we have new information that NVIDIA will launch an updated GeForce RTX 3060 GPU SKU that features a different ID, in the quest to limit card's mining performance. According to HKEPC, NVIDIA is producing updated GeForce RTX 3060 GKU SKUs with GA106-302 ID that should launch sometime in May, which are supposed to replace the GA106-300 SKUs now present. The software and the drivers will use the new ID to identify new SKUs and limit the performance of the card at mining tasks such as Ethereum mining. That way, it ensures that no driver version or bypass can trick the software to enable the card to use its full mining power and it shall render it unprofitable. Additionally, kopite7kimi, a known hardware leaker, claims that NVIDIA is also preparing updated GPU SKU IDs for GA104 and GA102 GPUs, with GA102-302/202 and GA104-302/202 variants supposedly coming.

An add-in card partner source shared with VideoCardz some juicy details about a pair of upcoming high-end GeForce RTX 30-series "Ampere" graphics cards. Called the GeForce RTX 3070 Ti and GeForce RTX 3080 Ti, the two are aimed to restore NVIDIA's competitiveness against the likes of AMD's recent Radeon RX 6000 series GPUs. It looks like NVIDIA doesn't want to play the memory size game just yet, despite giving the RTX 3060 12 GB of it.

The GeForce RTX 3070 Ti appears to be maxing out the GA104 silicon and carries the ASIC code "GA104-400-A#." The current RTX 3070 enables all but one of the TPCs on the GA104, working out to 5,888 CUDA cores. The new RTX 3070 Ti probably maxes out the GA104 to its CUDA core count of 6,144. The more substantial upgrade, however, is memory. The card ditches 14 Gbps GDDR6 for fast GDDR6X memory of an unknown speed—probably higher than 16 Gbps. The memory size remains 8 GB, across 256-bit.

We are just a few weeks away from the launch of NVIDIA's latest GeForce RTX 3060 graphics cards based on the new Ampere architecture, and there is already some news regarding the lineup position and its possible distortion. According to multiple sources over at Overclocking.com, NVIDIA is set to re-introduce its previous generation GeForce RTX 2060 and RTX 2060 SUPER graphics cards to the market. Once again. The source claims that NVIDIA is already pushing the stock over to its board partners and system integrators to use the last-generation product. So far, it is not clear why the company is doing this and we can only speculate on it.

The source also claims that the pricing structure of the old cards will be 300 EUR for RTX 2060 and 400 EUR for RTX 2060 SUPER in Europe. The latter pricing models directly competes with the supposed 399 EUR price tag of the upcoming GeForce RTX 3060 Ti model, which is based on the newer Ampere uArch instead of the last-gen Turing cards. The possibility for such a move is a possible scarce of GA106/GA104 silicon needed for the new cards, and the company could be aiming to try and satisfy the market with left-over stock from the previous generation cards.

NVIDIA is reportedly preparing a new GeForce RTX 30-series SKU positioned around the RTX 3060 Ti and the RTX 3070, as the company looks to fine-tune its lineup against the Radeon RX 6700 series. Called the GeForce RTX 3060 Ultra, the SKU is reportedly carved out from the same 8 nm "GA104" silicon as the RTX 3060 Ti and RTX 3070; but with a different core-configuration, and 12 GB of GDDR6 memory. At this point, it is not known if the memory bus width is narrowed to 192-bit, or if the same 256-bit wide memory bus is used (with mixed memory chip density). WCCFTech posted a picture of the first custom-design RTX 3060 Ultra card, an ASUS TUF Gaming product, which it reports to be faster than the RTX 3060 Ti. The publication also reports the card's MSRP pricing to be USD $449.

With the desktop GeForce RTX 3080 being based on the "big" GeForce Ampere silicon, the "GA102," we wondered how NVIDIA would go about designing the RTX 3080 Mobile. It turns out that the company will max out the smaller "GA104" silicon on which the desktop RTX 3070 and RTX 3060 Ti, are based. An unreleased ASUS ROG Zephyrus Duo (GX551QS) gaming notebook's Geekbench online database entry reveals the name-string and streaming multiprocessor (SM) count of the RTX 3080 Mobile.

The Geekbench online database entry lists out the OpenCL device (GPU) name-string as "GeForce RTX 3080 Laptop GPU," and OpenCL compute unit (SM) count as 48. This corresponds with the maximum SM count of the "GA104," which features 6,144 Ampere CUDA cores spread across 24 TPCs (48 SM), 48 2nd generation RT cores, 192 3rd generation Tensor cores, 192 TMUs, and 96 ROPs. The Geekbench entry also reveals the video memory amount as 16 GB, maxing out the 256-bit wide GDDR6 memory interface of the "GA104," likely using 16 Gbit memory chips.

A new HP OEM GeForce driver points to the two distinct approaches NVIDIA is possibly taking to develop its new high-end GeForce RTX 30-series SKU positioned between the $699 RTX 3080 and the $1,499 RTX 3090; particularly in the wake of the $999 AMD Radeon RX 6900 XT launch. The OEM driver's GPU support list references a number of unreleased graphics cards based on the "GA102" silicon, including engineering samples of 11 GB and 12 GB variants of the RTX 3080; and an RTX 3080 Ti.

The 11 GB and 12 GB variants of the RTX 3080 (which are unreleased engineering samples at this point) could possibly be SKUs carved out with the same core-configuration as the RTX 3080, but with slightly wider memory interfaces, with the 11 GB variant using a 352-bit interface, and the 12 GB variant maxing out the full 384-bit interface of the "GA104," albeit with 8 Gbit memory chips, unlike the RTX 3090, which uses twenty four 8 Gbit chips (2 per 32-bit path), to achieve 24 GB. The RTX 3080 Ti appears to be a whole different beast. Although the HP document doesn't mention its core-configuration or memory size, older reports have pointed at the possibility of this SKU featuring 9,984 CUDA cores, and the full 384-bit wide memory bus (possibly with 12 GB of memory). Even older reports point to the likelihood of the RTX 3080 Ti retaining the 320-bit memory bus of the RTX 3080, but doubling the memory amount to 20 GB.

NVIDIA today announced the GeForce RTX 3060 Ti, its new performance-segment graphics card that logically succeeds the GeForce RTX 2060 Super, at a starting MSRP of USD $399, with availability slated for December 2, 2020. The GPU is based on the same 8 nm "GA104" silicon as the $499 RTX 3070, but is heavily cut down, in featuring 38 out of 48 SMs (19 out of 24 TPCs), resulting in 4,864 CUDA cores, 152 Tensor cores, 38 RT cores, 152 TMUs, and 80 ROPs.

The RTX 3060 Ti is endowed with the same memory setup as the RTX 2060 Super—8 GB of 256-bit GDDR6 at 14 Gbps, yielding 448 GB/s bandwidth. NVIDIA developed a Founders Edition card based on the RTX 3060 Ti, which resembles the RTX 3070 Founders Edition with the exception of silvery metal replacing the gunmetal on the cooler frame. NVIDIA's various AIC partners have also announced their custom-design graphics cards. NVIDIA claims that the RTX 3060 Ti performs on par with the RTX 2080 Super, making it a beast for 1440p gaming with RTX-on. We put this claim to the test across our six launch-day reviews linked below.

Read the TechPowerUp reviews of NVIDIA RTX 3060 Ti Founders Edition, ASUS RTX 3060 Ti STRIX OC, Gigabyte RTX 3060 Ti Gaming OC Pro, MSI RTX 3060 Ti Gaming X Trio, Palit RTX 3060 Ti GamingPro OC, Zotac RTX 3060 Ti Twin Edge

3DMark scores of the upcoming NVIDIA GeForce RTX 3060 Ti were leaked to the web by VideoCardz. The RTX 3060 Ti was put through standard 3DMark Fire Strike and Time Spy benchmark runs. In the DirectX 11-based Fire Strike benchmark, the card allegedly scores 30706 points, with 146.05 FPS in GT1 and 122 FPS in GT2. With the newer DirectX 12-based Time Spy test, it allegedly scores 12175 points, with 80.82 FPS in GT1, and 68.71 FPS in GT2. There are no system specs on display, but the scores put the RTX 3060 Ti slightly ahead of the previous-generation high-end GeForce RTX 2080 Super.

The GeForce RTX 3060 Ti, bound for a December 2 launch, is an upcoming performance-segment graphics card based on the "Ampere" architecture, and is carved out of the same 8 nm "GA104" silicon as the RTX 3070. It reportedly packs 4,864 "Ampere" CUDA cores, 38 second-gen RT cores, 152 third-gen Tensor cores, and the same memory configuration as the RTX 3070—8 GB of 14 Gbps GDDR6 across a 256-bit wide bus. NVIDIA is targeting a "<$399" price-point, making the card at least 43% cheaper than the RTX 2080 Super.

CPU Infotech, a Bosnian retailer of computer hardware, recently posted a photo of their latest inventory entries on Facebook. The photo showcased the newly/received Gigabyte RTX 3060 Ti EAGLE graphics cards, one of Gigabyte's designs for this particular SKU. The RTX 3060 Ti EAGLE features a dual-slot, dual-fan cooler design that's the smallest seen on any Ampere graphics card to date. The retailer announces that the inventory should be for sale pretty soon - and all publicly available information points towards a December 2nd release date for the RTX 3060 Ti.

The RTX 3060 Ti is supposed to beat NVIDIA's previous RTX 2080 SUPER graphics cards in performance, whilst costing half of that cards' launch asking price at $399. This should make this one of the most interesting performance-per-dollar graphics cards in NVIDIA's lineup. The RTX 3060 Ti is reportedly based on the same 8 nm "GA104" silicon as the RTX 3070, with further cuts. It features 38 out of the 48 available streaming multiprocessors on "GA104". This amounts to 4,864 "Ampere" CUDA cores, 152 tensor cores, and 38 "Ampere" RT cores. The memory configuration is unchanged from the RTX 3070, which translates to 8 GB of 14 Gbps GDDR6 memory across a 256-bit wide memory interface, with 448 GB/s of memory bandwidth. This marks the first time in years NVIDIA has launched a Ti model before the regular-numbered SKU in a given series, showcasing just how intense AMD competition is expected to be.

It looks like NVIDIA will launch its 4th GeForce RTX 30-series product ahead of Holiday 2020, the GeForce RTX 3060 Ti, with VideoCardz unearthing a leaked NVIDIA performance guidance slide, as well as pictures of custom-design RTX 3060 Ti cards surfacing on social media. The RTX 3060 Ti is reportedly based on the same 8 nm "GA104" silicon as the RTX 3070, but cut down further. It features 38 out of 48 streaming multiprocessors physically present on the "GA104," amounting to 4,864 "Ampere" CUDA cores, 152 tensor cores, and 38 "Ampere" RT cores. The memory configuration is unchanged from the RTX 3070, which means you get 8 GB of 14 Gbps GDDR6 memory across a 256-bit wide memory interface, with 448 GB/s of memory bandwidth.

According to a leaked NVIDIA performance guidance slide for the RTX 3060 Ti, the company claims the card to consistently beat the GeForce RTX 2080 SUPER, a $700 high-end SKU from the previous "Turing" generation. The same slide also shows a roughly 40% performance gain over the previous generation RTX 2060 SUPER, which is probably the logical predecessor for this card. In related news, PC Master Race (OfficialPCMR) on its Facebook page posted pictures of boxes of an ASUS TUF Gaming GeForce RTX 3060 Ti OC graphics cards, which confirms the existence of this SKU. The picture of the card on the box reveals a design similar to other TUF Gaming RTX 30-series cards launched by ASUS so far. As for price, VideoCardz predicts a $399 MSRP for the SKU, which should nearly double the price-performance for this card over the RTX 2080 SUPER at NVIDIA's performance numbers.

NVIDIA has reportedly delayed the launch of its GeForce RTX 3060 Ti performance-segment graphics card from mid-November to early-December, 2020. The RTX 3060 Ti is expected to be positioned a notch below the $500 RTX 3070, and based on the same 8 nm "GA104" silicon with 38 out of 48 streaming multiprocessors of the silicon enabled, amounting to 4,864 CUDA cores. The card is expected to come with the same exact memory setup as the RTX 3070, with 8 GB of 14 Gbps GDDR6 memory across a 256-bit wide bus. Besides a lighter core-configuration, the RTX 3060 Ti is expected to target a typical board power metric of 180 W, enabling designs with single 8-pin PCIe power connectors. Expreview, which broke the story on the launch delay predicts that the RTX 3060 Ti could perform similar to the RTX 2080 Super, a $700 high-end graphics card from the previous generation.

As for the delay, the RTX 3060 Ti was originally slated to be announced on November 17, but has its launch date pushed by two weeks, down to December 2. The reasons behind the delay could be anything from inventory building, to last-minute SKU optimization in the wake of AMD's Radeon RX 6000 series SKUs. Even the cheapest of the RX 6000-series SKUs announced so far, the RX 6800, is priced higher than the RTX 3070, and AMD claims higher performance than the RTX 2080 Ti (i.e. the card trades blows with the RTX 3070), which means the NVIDIA product stack could see many updates in the coming couple of months, some of which could even miss Holiday 2020 sales.

Fresh reports floating in the rumor mill's circulatory system claim that NVIDIA backtracked on its plans to launch higher VRAM capacity versions of their RTX 3080 and the (in the meantime, delayed) RTX 3070. These cards launched with 10 GB VRAM for the RTX 3080 and 8 GB VRAM for the RTX 3070, with reports circulating as early as their announcement that there would be double-capacity versions hitting the market just a few months later - specifically, in December of this year. Videocardz, however, claims that these long-rumored 20 GB and 16 GB SKUs have now been canceled by NVIDIA, who sent this news to its AIB partners - and the usage of canceled, not postponed, is perfunctory.

For cards theoretically shipping come December, this is indeed a small advance notice, but it might be enough for AIB partners to feed all their GA102-200 (RTX 3080) and GA104-400 (RTX 3070) silicon towards the already - if not readily - available models. This report, Videocardz claims, has been confirmed by two of their sources, and comes at the exact same day specifications for AMD's RX 6000 series leaked. It's likely NVIDIA already had knowledge of its competition's designs and performance targets, however, so this could be seen as nothing more than a coincidence. One of the publications' sources claims GDDR6X yields might be the cause for the cancellation, but this doesn't help explain why the alleged RTX 3070 16 GB card (with its GDDR6 chips) was also canceled. Remember: these are rumors on cards that were never announced by NVIDIA themselves, so take these with the appropriate salt-mine level of skepticism.