• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

PNY GeForce RTX 4070 Ti Super Verto OC

W1zzard

Administrator
Staff member
Joined
May 14, 2004
Messages
27,842 (3.71/day)
Processor Ryzen 7 5700X
Memory 48 GB
Video Card(s) RTX 4080
Storage 2x HDD RAID 1, 3x M.2 NVMe
Display(s) 30" 2560x1600 + 19" 1280x1024
Software Windows 10 64-bit
The PNY GeForce RTX 4070 Ti Super Verto, priced at the MSRP of $800, features a decent triple-slot, triple-fan cooler. This configuration ensures good temperatures and noise levels. Additionally, the card comes with an out-of-the-box overclock of +15 MHz, which, while not substantial, still contributes to enhanced performance.

Show full review
 
Joined
Oct 17, 2022
Messages
62 (0.08/day)
Memory bandwidth this, vram limits that. In the real world, turns out the arm chair architects were blowing things out of proportion. Who would have thought? Great review and well written conclusion.

Big fan of pny cards fwiw. My pny 4090 is cool and quiet in a solidly built, relatively small form factor.
 
Joined
Mar 1, 2021
Messages
115 (0.08/day)
Processor R7 7800X3D
Motherboard MSI B650 Tomahawk
Memory 2x32GB 6000CL30
Video Card(s) RTX 3070 FE
Case Lian Li O11 Air Mini
Power Supply Corsair RM1000x
Does anyone know if XLR8 4070 Ti Super uses thes same cooler as the XLR8 4070 Ti?

Memory bandwidth this, vram limits that. In the real world, turns out the arm chair architects were blowing things out of proportion.
Or you know, the card has bad launch day drivers?

Apparently expecting that more cuda cores, higher clock speeds and memory bandwidth should make the GPUs faster makes you an arm chair architect nowadays??
 
Joined
Oct 17, 2022
Messages
62 (0.08/day)
Does anyone know if XLR8 4070 Ti Super uses thes same cooler as the XLR8 4070 Ti?


Or you know, the card has bad launch day drivers?

Apparently expecting that more cuda cores, higher clock speeds and memory bandwidth should make the GPUs faster makes you an arm chair architect nowadays??
The gpu clock speeds are the same. It has only 10% more cuda cores than its non-super variant, and gets a real world 7-10% increase in performance. Shocker.
 

PATHGALORE

New Member
Joined
Jan 23, 2024
Messages
5 (0.02/day)
Are we going to ignore the fact that the 7900xt is more power efficient than 4070ti super?
Chiplet gpu on 5nm more efficient then monolithic gpu made on 4 nm?
LOL, so much for Nvidia efficiency...
 
Joined
Apr 17, 2021
Messages
564 (0.43/day)
System Name Jedi Survivor Gaming PC
Processor AMD Ryzen 7800X3D
Motherboard Asus TUF B650M Plus Wifi
Cooling ThermalRight CPU Cooler
Memory G.Skill 32GB DDR5-5600 CL28
Video Card(s) MSI RTX 3080 10GB
Storage 2TB Samsung 990 Pro SSD
Display(s) MSI 32" 4K OLED 240hz Monitor
Case Asus Prime AP201
Power Supply FSP 1000W Platinum PSU
Mouse Logitech G403
Keyboard Asus Mechanical Keyboard
Are we going to ignore the fact that the 7900xt is more power efficient than 4070ti super?
Chiplet gpu on 5nm more efficient then monolithic gpu made on 4 nm?
LOL, so much for Nvidia efficiency...
Yeah it actually surprised me how inefficient this chip is. The RTX 4080 was top of the charts for efficiency, not this one. This card isn't any better than the 7800 XT 7900 XT or XTX. In fact the XTX is much better. Surprising.
 
Joined
Mar 1, 2021
Messages
115 (0.08/day)
Processor R7 7800X3D
Motherboard MSI B650 Tomahawk
Memory 2x32GB 6000CL30
Video Card(s) RTX 3070 FE
Case Lian Li O11 Air Mini
Power Supply Corsair RM1000x
The gpu clock speeds are the same. It has only 10% more cuda cores than its non-super variant, and gets a real world 7-10% increase in performance. Shocker.
I was comparing it to 4080 since they both use the same AD103 die, 4070Ti Super is clocked higher (2.6GHz vs 2.5), has almost the same mem bandwidth and ~15% less cuda cores. In reality this should be closer to RTX 4080 in performance (like within 5-10%), but i suspect something is off with pre release drivers, which is also something that Steve from HUB ran into and Nvidia supplied him with updated firmware (which strangely didnt make much a difference)
 
Joined
Jan 22, 2024
Messages
86 (0.28/day)
Processor 7800X3D
Cooling Thermalright Peerless Assasin 120
Memory 32GB at 6000/30
Video Card(s) 7900 XT soon to be replaced by 4080 Super
Storage WD Black SN850X 4TB
Display(s) 1440p 360 Hz IPS + 34" Ultrawide 3440x1440 165 Hz IPS ... Hopefully going OLED this year
Are we going to ignore the fact that the 7900xt is more power efficient than 4070ti super?
Chiplet gpu on 5nm more efficient then monolithic gpu made on 4 nm?
LOL, so much for Nvidia efficiency...
What are you talking about, 7900 XT uses 20 watts more in gaming here.

Chiplet / MCM literally SHOULD use much less power than monolithic. Yet AMD failed here. They tried to pull a Ryzen on the GPU market but failed.


And i quote

"Nvidia's Ada Lovelace architecture clearly reigns as the power efficiency champion — we have performance per watt data in the tables at the bottom of the page. The new 4070 Ti Super has a TGP (total graphics power) rating of 285W, the same as the vanilla 4070 Ti. In our test suite, it averaged 224W at 1080p medium, 249W at 1080p ultra, 268W at 1440p ultra, and 283W at 4K ultra. That's about 15–20 watts more than the 4070 Ti Founders Edition at each setting, but still below the rated TGP in most cases.

Performance on average comes very close to matching the RX 7900 XTX, while drawing about 75W less power. It also outperforms the 7900 XT by around 13% and uses about 25–50 watts less power, and ranges from 5W less to 30W more power than the RX 7800 XT while delivering up to 45% more performance.

In general, the RTX 40-series GPUs are roughly 30–50 percent more efficient than AMD's competing RX 7000-series RDNA 3 GPUs."

The gpu clock speeds are the same. It has only 10% more cuda cores than its non-super variant, and gets a real world 7-10% increase in performance. Shocker.
True, 4070 to 4070 SUPER was a 22% improvement in cores, resulted in ~15% performance.

4070 Ti to 4070 Ti SUPER is 10% improvement in cores, the VRAM and bus width don't really affect performance much since it was not a limiting factor to begin with and the end result is 5-6% which is the same increase as 4070 to 4070 SUPER percentage-wise.

The bus width helps slightly more in 4K, but who really buys this card for native 4K gaming, most 4K gamers I know use DLSS or FSR anyway.

Personally I look at 1440p testing. The middle-ground. Don't care about 1080p or 4K really. I did not use 1080p for years and the 1440p result is going to be more in line with 4K using DLSS/FSR anyway.

Many 4K gamers even uses DLSS Performance mode which is 1080p internally but it looks quite decent actually.
 
Last edited:

PATHGALORE

New Member
Joined
Jan 23, 2024
Messages
5 (0.02/day)
Yeah, i am going to have to disagree with you.
 

Attachments

  • Screenshot_20240124_144107_Brave.jpg
    Screenshot_20240124_144107_Brave.jpg
    361.8 KB · Views: 454
Joined
Nov 26, 2021
Messages
1,648 (1.50/day)
Location
Mississauga, Canada
Processor Ryzen 7 5700X
Motherboard ASUS TUF Gaming X570-PRO (WiFi 6)
Cooling Noctua NH-C14S (two fans)
Memory 2x16GB DDR4 3200
Video Card(s) Reference Vega 64
Storage Intel 665p 1TB, WD Black SN850X 2TB, Crucial MX300 1TB SATA, Samsung 830 256 GB SATA
Display(s) Nixeus NX-EDG27, and Samsung S23A700
Case Fractal Design R5
Power Supply Seasonic PRIME TITANIUM 850W
Mouse Logitech
VR HMD Oculus Rift
Software Windows 11 Pro, and Ubuntu 20.04
What are you talking about, 7900 XT uses 20 watts more in gaming here.

Chiplet / MCM literally SHOULD use much less power than monolithic. Yet AMD failed here. They tried to pull a Ryzen on the GPU market but failed.


And i quote

"Nvidia's Ada Lovelace architecture clearly reigns as the power efficiency champion — we have performance per watt data in the tables at the bottom of the page. The new 4070 Ti Super has a TGP (total graphics power) rating of 285W, the same as the vanilla 4070 Ti. In our test suite, it averaged 224W at 1080p medium, 249W at 1080p ultra, 268W at 1440p ultra, and 283W at 4K ultra. That's about 15–20 watts more than the 4070 Ti Founders Edition at each setting, but still below the rated TGP in most cases.

Performance on average comes very close to matching the RX 7900 XTX, while drawing about 75W less power. It also outperforms the 7900 XT by around 13% and uses about 25–50 watts less power, and ranges from 5W less to 30W more power than the RX 7800 XT while delivering up to 45% more performance.

In general, the RTX 40-series GPUs are roughly 30–50 percent more efficient than AMD's competing RX 7000-series RDNA 3 GPUs."


True, 4070 to 4070 SUPER was a 22% improvement in cores, resulted in ~15% performance.

4070 Ti to 4070 Ti SUPER is 10% improvement in cores, the VRAM and bus width don't really affect performance much since it was not a limiting factor to begin with and the end result is 5-6% which is the same increase as 4070 to 4070 SUPER percentage-wise.

The bus width helps slightly more in 4K, but who really buys this card for native 4K gaming, most 4K gamers I know use DLSS or FSR anyway.

Personally I look at 1440p testing. The middle-ground. Don't care about 1080p or 4K really. I did not use 1080p for years and the 1440p result is going to be more in line with 4K using DLSS/FSR anyway.

Many 4K gamers even uses DLSS Performance mode which is 1080p internally but it looks quite decent actually.
Chiplet GPUs will always use more power than monolithic GPUs; that is the price of high speed off-chip interconnect, i.e. the connection between the MCDs and the GCD. The advantage, which hasn't manifested in consumer GPUs yet, is that you can build a much larger GPU than even the largest monolithic GPU. Contrast AMD's MI300X with the 7900 XTX; the MI300X dies have a collective 320 CUs compared to the 96 CUs for the 7900 XTX.
 
Joined
Feb 4, 2020
Messages
3 (0.00/day)
In November TPU chose PNY as special partner for GPU reviews but since June there are zero XLR8 reviews. No Tis, no Supers, nothing. Hate to see this plain model being THE hottest of the lot and among the loudest.
 

W1zzard

Administrator
Staff member
Joined
May 14, 2004
Messages
27,842 (3.71/day)
Processor Ryzen 7 5700X
Memory 48 GB
Video Card(s) RTX 4080
Storage 2x HDD RAID 1, 3x M.2 NVMe
Display(s) 30" 2560x1600 + 19" 1280x1024
Software Windows 10 64-bit
In November TPU chose PNY as special partner for GPU reviews but since June there are zero XLR8 reviews. No Tis, no Supers, nothing. Hate to see this plain model being THE hottest of the lot and among the loudest.
Yeah I would have loved to have XLR8 for Super reviews, too. Will discuss with PNY. But at least this clears up any conspiracy theories that we're giving them special treatment in the reviews
 
Joined
Oct 17, 2022
Messages
62 (0.08/day)
In November TPU chose PNY as special partner for GPU reviews but since June there are zero XLR8 reviews. No Tis, no Supers, nothing. Hate to see this plain model being THE hottest of the lot and among the loudest.
I just realized XLR8 is short for accelerate
 
Joined
Jul 20, 2020
Messages
1,127 (0.71/day)
System Name Gamey #1 / #3
Processor Ryzen 7 5800X3D / Ryzen 7 5700X3D
Motherboard Asrock B450M P4 / MSi B450 ProVDH M
Cooling IDCool SE-226-XT / IDCool SE-224-XTS
Memory 32GB 3200 CL16 / 16GB 3200 CL16
Video Card(s) PColor 6800 XT / GByte RTX 3070
Storage 4TB Team MP34 / 2TB WD SN570
Display(s) LG 32GK650F 1440p 144Hz VA
Case Corsair 4000Air / TT Versa H18
Audio Device(s) Dragonfly Black
Power Supply EVGA 650 G3 / EVGA BQ 500
Mouse JSCO JNL-101k Noiseless
Keyboard Steelseries Apex 3 TKL
Software Win 10, Throttlestop
What are you talking about, 7900 XT uses 20 watts more in gaming here.

And it gets more FPS. Efficiency is a ratio, W1zz calculates and reports it. In this very review you're commenting on!

The 7900 XT is slightly more efficient than the 4070 TiTi, denial doesn't change that.
 

Talon

New Member
Joined
Apr 22, 2022
Messages
7 (0.01/day)
Looking at the PCB analysis, what is that additional phase on the north side of the card that is not counted? Is that not the 9th phase?
 

W1zzard

Administrator
Staff member
Joined
May 14, 2004
Messages
27,842 (3.71/day)
Processor Ryzen 7 5700X
Memory 48 GB
Video Card(s) RTX 4080
Storage 2x HDD RAID 1, 3x M.2 NVMe
Display(s) 30" 2560x1600 + 19" 1280x1024
Software Windows 10 64-bit
Looking at the PCB analysis, what is that additional phase on the north side of the card that is not counted? Is that not the 9th phase?
You are right, I missed it, fixed
 
Joined
Mar 15, 2024
Messages
3 (0.01/day)
Location
Hungary
Processor Intel i9 13700K (5.4/4.4)
Motherboard ASUS Maximus Z690 Hero
Cooling NZXT Kraken X72
Memory 32GB Corsair Vengeance DDR5 5600(->6600)
Video Card(s) Kfa2 RTX 3080 SG 10GB
Storage Samsung 970 Evo Plus 250GB NVMe
Display(s) Acer Predator XB271HU 27"
Case HAF 932 AMD Dragon Edition
Audio Device(s) ASUS Xonar DGX
Power Supply Corsair RM750x
Mouse ASUS Gladius II Origin
Keyboard ASUS ROG Strix Flare
Software W11
may i have a question?!
if i see the rev about the 4070Ti, the average fps in 1440p is 170FPS.... and if i check the 4070Ti Super rev this number is 137FPS... is tis OK?! how is this possible?!
_o_
 
Joined
Jul 20, 2020
Messages
1,127 (0.71/day)
System Name Gamey #1 / #3
Processor Ryzen 7 5800X3D / Ryzen 7 5700X3D
Motherboard Asrock B450M P4 / MSi B450 ProVDH M
Cooling IDCool SE-226-XT / IDCool SE-224-XTS
Memory 32GB 3200 CL16 / 16GB 3200 CL16
Video Card(s) PColor 6800 XT / GByte RTX 3070
Storage 4TB Team MP34 / 2TB WD SN570
Display(s) LG 32GK650F 1440p 144Hz VA
Case Corsair 4000Air / TT Versa H18
Audio Device(s) Dragonfly Black
Power Supply EVGA 650 G3 / EVGA BQ 500
Mouse JSCO JNL-101k Noiseless
Keyboard Steelseries Apex 3 TKL
Software Win 10, Throttlestop
may i have a question?!
if i see the rev about the 4070Ti, the average fps in 1440p is 170FPS.... and if i check the 4070Ti Super rev this number is 137FPS... is tis OK?! how is this possible?!
_o_

Different games. Use the navigation popup to have a look at the list in each review as W1zz updates with new ones and drops old ones as needed.
 
Joined
Mar 15, 2024
Messages
3 (0.01/day)
Location
Hungary
Processor Intel i9 13700K (5.4/4.4)
Motherboard ASUS Maximus Z690 Hero
Cooling NZXT Kraken X72
Memory 32GB Corsair Vengeance DDR5 5600(->6600)
Video Card(s) Kfa2 RTX 3080 SG 10GB
Storage Samsung 970 Evo Plus 250GB NVMe
Display(s) Acer Predator XB271HU 27"
Case HAF 932 AMD Dragon Edition
Audio Device(s) ASUS Xonar DGX
Power Supply Corsair RM750x
Mouse ASUS Gladius II Origin
Keyboard ASUS ROG Strix Flare
Software W11
OK.
now i have no idea what to buy?! Gainward or (this) PNY version of 70TiS....
my last GW card was a 3070Ti.... PNY never stayed in my pc case.... tried to find any "feedback" about the PNY cards... nothing helpful...
 
Joined
Sep 27, 2008
Messages
1,196 (0.20/day)
OK.
now i have no idea what to buy?! Gainward or (this) PNY version of 70TiS....
my last GW card was a 3070Ti.... PNY never stayed in my pc case.... tried to find any "feedback" about the PNY cards... nothing helpful...

If it's the Gainward is the Super Phoenix model that was reviewed

I'd lean towards the Gainward because it has a better and quieter cooler.
 

rozplay

New Member
Joined
Sep 17, 2024
Messages
19 (0.27/day)
@W1zzard Thanks for the review. The graphs indicate that this card has a fan stop feature, but everything I've read says that it actually has a minimum of 30% RPM....
 
Top