NVIDIA’s RTX 40 series GPUs are just a couple of months away, but we still haven’t got the full specs of these next-gen GPUs. We did receive some rumored specifications last month from Kopite7kimi, but the same leaker gave away changed specifications of the RTX 4090, 4070, and now, the RTX 4080.
Leaker Kopite7kimi has provided updated specifications for NVIDIA RTX 4080. There is only an update to CUDA Core specs, now rumored at 9728. This means a downgrade from 80 active Streaming Multiprocessors to 76. This is a reduction from the previously speculated 10240 CUDA cores or 80 SMs.
Mostly we see changes in rumored specs due to the leakers being inaccurate, but here it might be the case of NVIDIA making several revision changes over the product’s pre-launch cycle & as such, the specifications change a lot.
RTX 4080 Rumored Specifications
The RTX 4080 will be based on the cut-down AD103-300 GPU, featuring 9728 CUDA cores or 76 SMs enabled of the total 84 units. The graphics card has GDDR6 memory support and will be launched a month after the flagship RTX 4090.
The RTX 4080 will require 420W of power by default, and it should ship with 16GB 256-bit GDDR6X memory. Judging from new specs, all thus far confirmed high-end RTX 40 models are to feature 21 Gbps modules.
The RTX 4080 will be the second 40-series graphics card to release, and while the official pricing hasn’t been revealed, we are speculating it to cost $699, similar to RTX 3080 and RTX 2080 GPUs. RTX 4080 is expected to be officially announced in October.
| RUMORED NVIDIA GeForce RTX 40 Series Specs | GeForce RTX 4090 | GeForce RTX 4080 | GeForce RTX 4070 |
| Architecture | Ada (TSMC N4) | Ada (TSMC N4) | Ada (TSMC N4) |
| GPU | AD102-300 | AD103-300 | AD104-400 (?) |
| Board Number | PG139-SKU330 | PG136/139-SKU360 | PG141-SKU331 |
| SMs | 128 | 80 → 76 | 60 |
| CUDA Cores | 16384 | 10240 → 9728 | 7680 |
| Base Clock | 2235 MHz | TBC | TBC |
| Boost Clock | 2520 MHz | TBC | TBC |
| Memory | 24 GB G6X | 16 GB G6X | 12GB G6 |
| Memory Bus | 384-bit | 256-bit | 192-bit |
| Memory Speed | 21 Gbps | 21 Gbps | 21 Gbps |
| Bandwidth | 1008 GB/s | 676 GB/s | 504 GB/s |
| TDP/TGP | ~450W | ~420W | ~300W |
| 3DMark TimeSpy Extreme | ~19,000 | ~15,000 | ~11,000 |
| Launch Date | October 2022 | TBC | TBC |
About Nvidia
NVIDIA Corporation is an American multinational technology company incorporated in Delaware, based in Santa Clara, California. They design graphics processing units (GPUs) for the gaming and professional markets, as well as system on chip units (SoCs) for the mobile computing and automotive market.
Best known for the “GeForce” lines of GPUs, they are a direct competitor to AMD’s “Radeon” series. NVIDIA has also expanded its offerings with its handheld game consoles Shield Portable, Shield Tablet, and Shield Android TV and its cloud gaming service GeForce Now.
No Comments on NVIDIA GeForce RTX 4080 Specs updated, Now Down to 9728 CUDA Cores