Leaker Suggests RTX 4060 Ti Has 160W TGP

Nvidia
(Image credit: Nvidia)

Nvidia has received a fair amount of criticism for its power hungry high-end GeForce RTX 40-series graphics cards based on the Ada Lovelace architecture. According to renowned hardware leaker @kopite7kimi, Nvidia is now looking to make its mainstream GeForce RTX 4060 Ti part a lot more power efficient.

As ever with leaks, take the news with a pinch until real world benchmarks and tests can be undertaken.

According to kopite7kimi, the GeForce RTX 4060 Ti will have a thermal graphics power of up to 160W instead of 220W reported initially. Meanwhile, general specifications of the product are set to remain generally the same: the board will be powered by the AD106 graphics processing unit with 4352 CUDA cores and accompanied by 8GB of 18 Gbps GDDR6 memory connected using a 128-bit interface. 

Right now, it is unclear how the new TGP affects GPU frequencies and performance of the GeForce RTX 4060 Ti and AD106 processor. With 4352 CUDA cores, the GeForce RTX 4060 Ti is already significantly behind rumored specifications of the GeForce RTX 4070, which allegedly has 5888 CUDA cores. If AD106's GPU clocks are dropped significantly from those planned initially, performance gap between GeForce RTX 4070 and RTX 4060 Ti will be significant. 

Swipe to scroll horizontally
Nvidia GeForce RTX 40-Series Specifications
Row 0 - Cell 0 GPUFP32 CUDA CoresMemory ConfigurationTBP
GeForce RTX 4090AD1021638424GB 384-bit 21 GT/s GDDR6X450W
GeForce RTX 4080AD103972816GB 256-bit 22.4 GT/s GDDR6X320W
GeForce RTX 4070 TiAD104768012GB 192-bit 21 GT/s GDDR6X285W
GeForce RTX 4070AD104?5888?12GB 192-bit 21 GT/s GDDR6X?250W?
GeForce RTX 4060 TiAD106?4352?8GB 128-bit 18 GT/s GDDR6?160W?

With 8GB of 128-bit GDDR6 memory, Nvidia's GeForce RTX 4060 Ti could offer a memory bandwidth that is 43% lower compared to that of the GeForce RTX 4070, so the gap between two products in memory bandwidth-dependent workloads (e.g., in high resolutions and/or with antialiasing enabled) may be huge. Meanwhile, the new product will also feature a 36% lower memory bandwidth than its direct predecessor, the GeForce RTX 3060 Ti with GDDR6 memory. Of course, we would expect 32MB of L2 cache to somewhat reduce bandwidth limitations, but only tests will reveal whether this is the case. 

Meanwhile, carrying only 8GB of memory is another peculiarity that can also be seen as a limitation. We already felt the 8GB of memory on the GeForce RTX 3060 Ti, 3070, and 3070 Ti was becoming a limiting factor and those are outgoing products launched in 2020 – 2021. Despite all these factors,  the GeForce RTX 4060 Ti is still likely to join the ranks of the best graphics cards as it will easily outperform its predecessor. 

With a 160W TGP, the GeForce RTX 4060 Ti could position itself as a viable graphics solution for small form factor gaming PCs. The board is rumored to feature a very short reference design, so expect Nvidia's partners to offer dual-slot boards for Mini-ITX machines and perhaps even single-slot variants for thin PCs. 

Keep in mind that we are talking about specifications leaked by an unofficial source, so take them with a pinch of salt, though it is plausible that Nvidia decided to build an energy-efficient yet powerful GPU to better compete for compact gaming PCs.  

Anton Shilov
Contributing Writer

Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • ingtar33
    how is a TDP of 160W on a card that probably draws over 250W of power "power efficient"?

    what universe is this? I remember the nvidia 970 and 1060 both drew low enough power you could almost get away with passive cooling them as long as you weren't overclocking them. but here we are talking about a power draw along the lines of a 80 series gpu just 2 generations ago as "power efficient"
    Reply
  • cknobman
    Nvidia makes stuff like this because they know there are suckers out there that will buy it.
    Reply
  • peachpuff
    cknobman said:
    Nvidia makes stuff like this because they know there are suckers out there that will buy it.
    That's like... business 101 no?
    Reply
  • PlaneInTheSky
    Way too high. A 1060 consumes far less and that is still one of the most used cards on Steam.

    With electricity prices being so high in many places around the world, this is a power hungry GPU and CPU generation I will just skip.

    Hopefully ARM becomes more mainstream for PC like it did for Apple, at least they have power correctly under control.
    Reply
  • PlaneInTheSky
    how is a TDP of 160W on a card that probably draws over 250W of power "power efficient"?

    what universe is this? I remember the nvidia 970 and 1060 both drew low enough power you could almost get away with passive cooling them as long as you weren't overclocking them. but here we are talking about a power draw along the lines of a 80 series gpu just 2 generations ago as "power efficient"

    lol yep

    Just bought a lightbulb the other day. It uses 7 watt like any other lightbulb nowadays. My sister reminded me to turn them off when I'm not in my room to save energy.

    Meanwhile this GPU will use 200+ watt and is called "efficient". Just lol, it would literally be the item using most electricity in our household. Yes our washing machine can use more, but it is only turned on for like 40 minutes twice a week. These companies live in an alternate universe where electricity is free and they haven't been paying attention to anything going on in the world.
    Reply
  • DavidLejdar
    If it will be performance-wise a solid fit for 1440p gaming, then it may become quite popular with such power consumption and size, if reasonably priced. But yeah, I prefer having 12 GB, which is so far more of a "just in case" thing than a necessity though.

    ingtar33 said:
    how is a TDP of 160W on a card that probably draws over 250W of power "power efficient"? ...

    Compared to higher-tier GPUs, it is quite low. And sure, it may be too much for some. Personally, having a GPU with around 200W (at peak), that's some 130W more than I had with 1050 Ti, which didn't really carry a lot of newer games, let alone at 1440p. And with an average of perhaps 10 hours of gaming a week, that's less than 2 kWh extra, or less than 10 kWh a month.
    Reply
  • PlaneInTheSky
    Compared to higher-tier GPUs, it is quite low.

    160W TDP for a xx60 series card is not low at all.

    That's around what GTX 1080 used which had a TDP of 180W.

    The amount of power GPU are using the last 2 generations is out of control.

    GTX 1070 = TDP 150W.
    RTX 4070 = TDP 285W

    GTX 1080 = TDP 180W.
    RTX 4080 = TDP 320W.

    And Nvidia and AMD dare to call their new GPU efficient.
    Reply
  • Eximo
    PlaneInTheSky said:
    160W TDP for a xx60 series card is not low at all.

    That's around what GTX 1080 used which had a TDP of 180W.

    The amount of power GPU are using the last 2 generations is out of control.

    And Nvidia and AMD dare to call their new GPU efficient.

    GTX 1070 = TDP 150W @ 6.42 TFLOPS = 428 GFLOPS/Watt
    RTX 4070 Ti = TDP 285W @ 40.1 TFLOPS = 1407GFLOPS/Watt

    GTX 1080 = TDP 180W @ 8.87 TFLOPS = 500 GFLOPS/Watt
    RTX 4080 = TDP 320W @ 48.8 TFLOPS = 1500 GFLOPS/Watt

    So about 3 times as efficient overall. You could always set a power limit.
    Reply
  • Amdlova
    Efficiency is buy a mac mini 699us... nvidia will charge for a 4060ti 128bit (128bits graphics) same a mac mini... (all system for one anemic graphics).
    Reply
  • atomicWAR
    Nice to see lower numbers for wattage but we already know the price won't be low. I fully expect $675 plus pricing. Smh sad dayz.
    Reply