NVIDIA GeForce RTX 4060 Ti & RTX 4060 Rumored To Feature Over 2.5 GHz Clocks, Top Model Faster Than An RTX 3080 10 GB 1

NVIDIA GeForce RTX 4060 reportedly slower than RTX 3070 Ti, AD106 and AD107 GPUs use PCIe x8 interface

In a new tweet, Kopite7kimi said that NVIDIA’s GeForce RTX 4060 graphics cards might not be very fast and might use a PCI x8 interface.

NVIDIA GeForce RTX 4060 series reportedly won’t get same upgrades as high-end Ada Lovelace GPUs

The leaker says the performance of the NVIDIA AD106 GPU, which is expected to power the RTX 4060 series graphics cards, isn’t very strong. We don’t know what specific configuration it is, but it’s likely it’s referring to the full-fat die rather than a scale model. An alleged 3DMark Time Spy Extreme benchmark has been shared and the GPU is said to score less than 7000 points. A score like this should make the AD106 GPU slower than the RTX 3070 Ti and on par with the RTX 3070, which doesn’t seem like the huge upgrade the high-end AD102 and AD103 GPUs get.

A Time Spy Extreme score between 6500 and 7000 should put the AD106 GPU (GeForce RTX 4060) up to 18% faster than the RTX 3060 Ti and 69% faster than the RTX 3060. Now a performance boost of over 50% is pretty huge but it’s not as big as the 2x jumps we’ve seen for high end cards. If there is a 50-60% jump in synthetic benchmarks, the game would see a 30-40% increase at best. So it looks like we will mostly get RTX 3070 performance levels in the next **60 card.

Additionally, the leaker also mentions that the AD106 and AD107 “Ada Lovelace” GPUs will use a PCIe x8 interface. Considering these GPUs are primarily aimed at the mobility segment (laptops/notebooks), this makes sense. For desktops, this means the GeForce RTX 4060 and 4050 will get an x8 link, which shouldn’t be a problem for most PCs, given that next-gen systems from AMD and Intel are ship with support for PCIe Gen 5 slots but work on an older Gen 3 platform may cause issues related to reduced bandwidth and transfer speeds.

0

4000

8000

12000

16000

20000

24000

NVIDIA GeForce RTX 4060 “expected” specs

Based on NVIDIA’s decision to do a mix of AD104/AD106 or go AD106 in its RTX 4060 series lineup, we may see a scaled down RTX 4060 or one with a full configuration while the Ti may use a reduced AD104 configuration. The AD106 GPU will come with 32MB of L2 cache and up to 48 ROPs.

Clock speeds are not yet confirmed, but given that the TSMC 4N process is used, we expect clocks between 2.0 and 3.0 GHz. The higher than usual clock speed boost comes from NVIDIA jumping two nodes since the Ampere GPUs with the Samsung 8nm node were actually a 10nm process node with some optimizations. NVIDIA skips 7nm and goes straight for a 5nm node and not even the vanilla variant but an optimized version of it. With Pascal on the 16nm TSMC node, NVIDIA achieved a huge jump in frequency and we can expect a similar jump this time around as well.

When it comes to memory specs, the GeForce RTX 4060 is expected to rock 8GB GDDR6X capabilities that could achieve faster speeds of 20+ Gbps on a 128-bit bus interface for over 320 GB/s of bandwidth. . The “Ti” variant, if terminated with an AD104 GPU, could offer up to 12 GB of memory on a 192-bit bus interface. The GeForce RTX 4060 graphics card is also said to rock a 220W TGP, which is a 30% increase over the RTX 3060 and a 10% increase over the RTX 3060 Ti. This is a massive increase in TGP and performance has to be really good for NVIDIA to maintain its efficiency numbers.

NVIDIA GeForce RTX 4060 Series Preliminary Specs:

Graphics card name NVIDIA GeForce RTX 4060Ti NVIDIA GeForce RTX 4060 NVIDIA GeForce RTX 3060Ti NVIDIA GeForce RTX 3060
GPU name Ada Lovelace AD104? Ada Lovelace AD106 Ampere GA104-200 Ampere GA106-300
Process node TSCM 4N TSCM 4N Samsung 8nm Samsung 8nm
Die size ~300mm2 ~200mm2 395.2mm2 To confirm
Transistors To be determined To be determined 17.4 billion To confirm
CUDA Colors 5120? 4608 4864 3584
TMU / ROP TBD / 64 TBD / 48 152 / 80 112 / 64
Tensor / Cores RT To be determined To be determined 152 / 38 112 / 28
Basic Clock To be determined To be determined 1410MHz 1320MHz
Boost clock 2.2-2.6GHz 2.2-2.6GHz 1665MHz 1780MHz
Calculation FP32 ~24 TFLOPs ~21 TFLOPs 16 TFLOPs 13 TFLOPs
RT TFLOP To be determined To be determined 32 TFLOPs 25 TFLOPs
Tensor TOP To be determined To be determined 192 TOPs 101 BEST
Memory capacity 12 GB of GDDR6? 8 GB of GDDR6? 8 GB GDDR6 12 GB GDDR6
Memory bus 192 bit 128 bit 256 bit 192 bit
Memory speed To be determined To be determined 14 Gbps 16 Gbps
Bandwidth >448 GB/s >320 GB/s 448 Gbps 384 Gbps
TGP ~265W ~220W 175W 170W
Price (MSRP / FE) ~US$399 ~US$329 US$399 US$329
Launch (Availability) 1H 2023 1H 2023 December 2, 2020 February 25, 2021

Products mentioned in this article


#NVIDIA #GeForce #RTX #reportedly #slower #RTX #AD106 #AD107 #GPUs #PCIe #interface

Leave a Comment

Your email address will not be published.