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

NVIDIA Seemingly Producing Yet Another GTX 1650 Variant Based on TU-116

Raevenlord

News Editor
Joined
Aug 12, 2016
Messages
3,755 (1.15/day)
Location
Portugal
System Name The Ryzening
Processor AMD Ryzen 9 5900X
Motherboard MSI X570 MAG TOMAHAWK
Cooling Lian Li Galahad 360mm AIO
Memory 32 GB G.Skill Trident Z F4-3733 (4x 8 GB)
Video Card(s) Gigabyte RTX 3070 Ti
Storage Boot: Transcend MTE220S 2TB, Kintson A2000 1TB, Seagate Firewolf Pro 14 TB
Display(s) Acer Nitro VG270UP (1440p 144 Hz IPS)
Case Lian Li O11DX Dynamic White
Audio Device(s) iFi Audio Zen DAC
Power Supply Seasonic Focus+ 750 W
Mouse Cooler Master Masterkeys Lite L
Keyboard Cooler Master Masterkeys Lite L
Software Windows 10 x64
NVIDIA's GTX 1650 has already seen more action and revisions within its own generation than most GPUs ever have in the history of graphics cards, with NVIDIA having updated not only its memory (from 4 GB GDDR5 with 128 GB/s bandwidth to 4 GB GDDR6 memory for 192 GB/s bandwidth), but also by carving up different silicon chips to provide the same part to market. The original GTX 1650 made use of NVIDIA's TU117 chips with 896 CUDA cores, which was then superseded by the TU116-based GTX 1650 SUPER, which mightily increased the GTX 1650's execution units (1280) and bandwidth (256-bit bus). There was also a TU106-based GTX 1650, which was just bonkers - a chip originally used on the RTX 2060 was thus repurposed and cut-down.

Now, another TU-116 variant is also available, which NVIDIA carved down from its GTX 1650 SUPER chips. These go back to the original releases' 896 CUDA cores and 128-bit bus, whilst keeping the GDDR6 memory ticking at 12 Gbps and clocks set at 1410 MHz Base and 1590 MHz Boost. This card achieves feature parity with the TU106-based GTX 1650, but trades in the crazy 445 mm² TU106 die for the much more svelte 284 mm² TU116 one. NVIDIA seems to be doing what it can by cleaning house of any and all leftover chips in preparation for their next-gen release - consumer confusion be damned.



View at TechPowerUp Main Site
 
give us ampere gaming, already! almighty leatherjacket
 
No one asked for this.
 
OMG just give us the 3000 series already NVIDIA!!!
 
This means the wait for a new generation continues.
Wasn't there a news from several days ago that nVidia has just taped the new chips out?
 
thanks Nvidia!
 
Take my money.

This is ampere,. Right..
 
Have dies, will harvest. I honestly wonder where NVIDIA keeps them all.
 
Have dies, will harvest. I honestly wonder where NVIDIA keeps them all.
In a bin with a billion teirs apparently and side pockets with hidden pockets and a special turd shoot for those 940 discrete office GPU's.
 
So... that's the 15th variant, considering mobile chips...

20200720-161930.png


Now, another TU-116 variant is also available, which NVIDIA carved down from its GTX 1650 SUPER chips. These go back to the original releases' 896 CUDA cores and 128-bit bus, whilst keeping the GDDR6 memory ticking at 12 Gbps and clocks set at 14410 MHz Base

That's a lot of clock, @Raevenlord ... Nvidia sure isn't holding anything back :D
 
another reason to go with Big Navi is big navi drivers are stable.
 
This is most likely just OEMs wanting different specs for their respective parts, but I understand people like to hate.
 
yeah, Radeon drivers stable like a car on 3 wheels
$_10.JPG
 
Can I ask what do Radeon drivers have to do with this topic? I don't really see the connection :confused:

Fanboys, trolls ?

Nah, it can't be that. They probably just posted in the wrong thread, yeah it's probably that no doubt.
 
I made my decision a month ago in favor of ASUS 1660 Super MINI OC , and I do refuse starting over the game of research for plus or minus 3FPS.
 
I'm more interested in that ALF figurine.
 
Looking forward to the TU102 variant with 75% of the shader units lasered inactive. Surely NVIDIA has a pile of defective TU102's that could be repurposed, why stop at TU106?
 
Looking forward to the TU102 variant with 75% of the shader units lasered inactive. Surely NVIDIA has a pile of defective TU102's that could be repurposed, why stop at TU106?

they can still get away with this type of hubris if big navi drivers are unstable. we can expect stagnation in gpu price/performance/re-releases that no one asked for endlessly unless big navi drivers are stable at launch. so it's just a matter of time now, we will see. I hope AMD surprises us all personally, would love to give my money to the red team again
 
Let's be clear drivers probably ain't the single biggest reason Navi isn't selling that well. With that out of the way it's fair to say that Nvidia doesn't feel compelled to change their tried & tested strategy of milking the cow(s) dry, oh well the more things change the more they remain the same :shadedshu:
 
people are already confused as it is. I know this is what some would do to clear inventory but the amount of revisions they do is a little too much.
 
I guess the 1650 is just like the 1060, a million different versions. Nothing new really.
 
In case anyone's hoping for another 'EVGA 2060 KO' with the extra unlocked compute cores that put it at 2080 or 2080Ti levels of compute... No that wont happen again. Nvidia have already said that was a mistake and it shouldnt of happened.

I mean it could happen, But a very very very small chance of that as they are gonna be extra careful.
 
Back
Top