NVIDIA GeForce RTX 4080 reportedly has 16GB and 12GB AIC variants

Published: 5th Sep 2022, 05:48 GMT   Comments

Please note that this post is tagged as a rumor.

NVIDIA RTX 4080 with either 12GB of 16GB memory

NVIDIA Add-in-Board partners may be preparing two versions for upcoming RTX 4080 GPU.

Following rumors about two variants of RTX 4070 card, we now learn that board partners currently have access to two reference design for RTX 4080 model as well. The leaker claims one design has 12GB memory while the other is equipped with 16GB. Both versions would feature GDDR6X memory, but there is a difference in a number PCB layers for each model: 12 GB with 10-layer PCB and 16 GB with 12-layer PCB.

One should note that those SKUs described as 4080 by MEGASizeGPU do not necessarily have to be the same model. As we have already seen, NVIDIA tends to work on multiple models at once. NVIDIA RTX 3080, the predecessor to 4080, was already listed with 10GB, 12GB, 16GB and even 20GB. The latter was confirmed just yesterday.

The leaker also claims that the RTX 4090 reference design for board partners (note that’s not Founders Edition), will have a 14-layer PCB. For comparison, both RTX 3080 and RTX 3090 had 12-PCB AIC design rule, as revealed by Igor’sLAB before the cards even launched.

NVIDIA RTX 4080 Founder’s Edition design has recently been leaked, or so everyone believes. The picture may look sketchy, especially since the card was in a plastic bag, but as soon as one realizes that the new logo matches NVIDIA new official font, the picture shouldn’t be blindly ignored just yet.

Alleged GeForce RTX 4080, Source: @KittyYYuko

For now, RTX 4080 is expected to feature a new AD103 GPU with 9728 CUDA cores and TBP up to 340W. Two variants featuring either 16GB or 12GB memory could launch simultaneously, or what is more likely, NVIDIA would launch a cheaper model first and then decide if there is need for a more capable SKU.

RUMORED NVIDIA GeForce RTX 40 Series Specs
VideoCardz.comGeForce RTX 4090GeForce RTX 4080GeForce RTX 4070
ArchitectureAda (TSMC 4N)Ada (TSMC 4N)Ada (TSMC 4N)
GPUAD102-300AD103-300AD104-400 (?)
Board NumberPG139-SKU330PG136/139-SKU360PG141
SMs
 
128
 
76
 
56 or 60
CUDA Cores
 
16384
 
9728
 
7168-7680
Base Clock
 
2235 MHz
TBCTBC
Boost Clock
 
2520 MHz
TBCTBC
Memory
 
24 GB G6X
 
16 or 12GB G6X
 
12GB or 10GB G6X
Memory Bus
 
384-bit
 
256 or 192-bit
 
192 or 160-bit
Memory Speed
 
21 Gbps
 
23 Gbps
 
21 Gbps
Bandwidth
 
1008 GB/s
 
736 or 552GB/s
 
504 or 420GB/s
Total Board Power
 
~450W
 
~340W
 
~250-285W
TimeSpy Extreme Perf.
 
~19,000
 
~15,000
 
~10,000-11,000
Launch DateOctober 2022TBCTBC

Source: MEGASizeGPU




Comment Policy
  1. Comments must be written in English.
  2. Comments deemed to be spam or solely promotional in nature will be deleted. Including a link to relevant content is permitted, but comments should be relevant to the post topic. Discussions about politics are not allowed on this website.
  3. Comments and usernames containing language or concepts that could be deemed offensive will be deleted. Note this may include abusive, threatening, pornographic, offensive, misleading, or libelous language.
  4. Comments complaining about the article subject or its source will be removed.
  5. A failure to comply with these rules will result in a warning and, in extreme cases, a ban. Please also note that comments that attack or harass an individual directly will result in a ban without warning.
  6. VideoCardz Moderating Team reserves the right to edit or delete any comments submitted to the site without notice.
  7. If you have any questions about the commenting policy, please let us know through the Contact Page.
Hide Comment Policy
Comments