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

NVIDIA Readies GeForce GTX 1650 SUPER with GDDR6 Memory for Late November

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,670 (7.43/day)
Location
Dublin, Ireland
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard Gigabyte B550 AORUS Elite V2
Cooling DeepCool Gammax L240 V2
Memory 2x 16GB DDR4-3200
Video Card(s) Galax RTX 4070 Ti EX
Storage Samsung 990 1TB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
It turns out that the GeForce GTX 1660 Super will be joined by another "Super" SKU by NVIDIA, the GeForce GTX 1650 Super, according to a VideoCardz report. Slated for a November 22 launch, the GTX 1650 Super appears to be NVIDIA's response to the Radeon RX 5500, which is being extensively compared to the current GTX 1650 in AMD's marketing material. While the core-configuration of the GTX 1650 Super is unknown, NVIDIA is giving it 4 GB of GDDR6 memory across a 128-bit wide memory interface, with a data-rate of 12 Gbps, working out to 192 GB/s of memory bandwidth. In comparison, the GTX 1650 uses 8 Gbps GDDR5 and achieves 128 GB/s memory bandwidth.

It remains to be seen just how much the improved memory subsystem helps the GTX 1650 Super catch up to the RX 5500, given that a maxed out TU117 silicon only has 128 more CUDA cores on offer, and AMD is claiming a 37% performance lead over the current GTX 1650 for its RX 5500. One possible way it can create the GTX 1650 Super is by tapping into the larger "TU116" silicon with 1/3rd of its memory interface disabled, and fewer CUDA cores than the GTX 1660. We'll know more in the run up to November 22.



View at TechPowerUp Main Site
 
Stahp already, and bring on 3000 series news instead. I'm just about fed up with Turing products after two full stacks AND a refresh.

Everybody knows 7nm is the one to wait for, stop wasting our time tyvm
 
One possible way it can create the GTX 1650 Super is by tapping into the larger "TU116" silicon with 1/3rd of its memory interface disabled, and fewer CUDA cores than the GTX 1660. We'll know more in the run up to November 22.
I've heard it used the NVEC encoder so this makes sense since I don't believe TU117 has it?
 
I've heard it used the NVEC encoder so this makes sense since I don't believe TU117 has it?

tu117 has old Volta's nvenc, tu116 has newer and better Turing nvenc. Decoder is the same on both. But yeah if it uses tu116, it would have better encoder and could be usable to OBS streamers.
 
Stahp already, and bring on 3000 series news instead. I'm just about fed up with Turing products after two full stacks AND a refresh.

Everybody knows 7nm is the one to wait for, stop wasting our time tyvm

Unfortunately, they have little reason to rush it.

The 12nm process is probably having excellent yelds by now (even considering the big dies) and in terms of performance/efficiency Nvidia is not under too much pressure from AMD.
 
Unfortunately, they have little reason to rush it.

The 12nm process is probably having excellent yelds by now (even considering the big dies) and in terms of performance/efficiency Nvidia is not under too much pressure from AMD.

Afraid so... The only thing on the near horizon might be Navi to put the pressure on.
 
Looks like Nvidia wants to get all the low budget GPU sales. By the time the 5500 launches these may come down in price and be all over the place. I am really keen to see how this stacks up against Polaris.
 
So they are cannibalizing the GDDR5 1660...

Ignorant if you ask me.

1660 should have gddr6 and then the new line of cards should all be gddr6 by that point. (Rtx3000/gtx1700)
 
So they are cannibalizing the GDDR5 1660...

Ignorant if you ask me.

1660 should have gddr6 and then the new line of cards should all be gddr6 by that point. (Rtx3000/gtx1700)

The 1660 is already 192 but so that is why they used the gddr5 stock up. Being GDDR6 would not have made it faster. However, going to GDDR6 will make a big difference on a 128 bit card.
 
tu117 has old Volta's nvenc, tu116 has newer and better Turing nvenc. Decoder is the same on both. But yeah if it uses tu116, it would have better encoder and could be usable to OBS streamers.

Now if we could only get a plugless, single slot, low profile adapter version, my server with Plex is waiting :)
 
So they are cannibalizing the GDDR5 1660...

Ignorant if you ask me.

1660 should have gddr6 and then the new line of cards should all be gddr6 by that point. (Rtx3000/gtx1700)
I doubt that faster memory on a 1650 would do that. It still has hella lot less shaders (896 vs 1404) so faster memory won't make it THAT MUCH better.
 
I doubt that faster memory on a 1650 would do that. It still has hella lot less shaders (896 vs 1404) so faster memory won't make it THAT MUCH better.

Well yeah, while full fat tu117 is 1024cc, that is still way too short from 1408cc what 1660 non-ti has. And Equal memory bandwidth won't change that fact.

Now if we could only get a plugless, single slot, low profile adapter version, my server with Plex is waiting :)

Nah I doubt that will ever come to fruition. Graphics cards that is single slot, plugless and low profile is something sub 30W TDP card. Cooling 75W TDP card on that configuration would be tall Oder

EDIT: Videocardz have spilled final specs for these cards. GTX 1650 Super should be cut down tu116 with 1280cc and 4GB 12Gbps gddr6 on 128bit bus. No pricing so they are obviously waiting for the RX 5500.

134907
 
Last edited:
That would be in fact pretty ok if those specs are real. From 896 shaders to 1280 gives a nice boost.
 
[NV promo for the card], i'll go for it ! :)

Messages1 (0.05/day)

Can't wait for 5500 to arrive, from what have been released, I can't see why NV is shitting its pants and releasing cards that, according to Nvidia CEO, only dumb people would buy.
 
Back
Top