Similar to the RTX 4070 specs from yesterday, we now have a specs update for the NVIDIA GeForce RTX 4080 graphics card too.

NVIDIA GeForce RTX 4080 Allegedly Gets Spec Bump: 9728 Cores, 16 GB GDDR6X Memory, 420W TBP, Around 30% Faster Than 3090 Ti

The similar leaker, Kopite7kimi, had beforehand posted a barely higher core configuration for the RTX 4080 but it surely must be pointed that NVIDIA makes a number of revision modifications over a product’s pre-launch cycle & as such, the specs change loads which Kopite7kimi is solely reporting. The card now has the identical quantity of cores and reminiscence albeit at a a lot decrease TGP than what was reported earlier.

I’m not a chatterbox, however I’ve to make some updates. I hope you do not thoughts.

a potential RTX 4080,




256bit 16G 21Gbps GDDR6X

complete energy ~420W

TSE ~15000

Now I’ve accomplished the most recent update for 4090, 4080 and 4070.

— kopite7kimi (@kopite7kimi) August 5, 2022

NVIDIA GeForce RTX 4080 ‘Expected’ Specifications

The NVIDIA GeForce RTX 4080 is anticipated to make the most of a cut-down AD103-300 GPU configuration with 9,728 cores or 76 SMs enabled of the whole 84 items whereas the earlier configuration provided 80 SMs or 10,240 cores. While the complete GPU comes full of 64 MB of L2 cache and as much as 224 ROPs, the RTX 4080 would possibly find yourself with 48 MB of L2 cache and decrease ROPs too resulting from its cut-down design.

NVIDIA GeForce RTX 4080 Graphics Card Now Reportedly Options 9728 Cores, 16 GB GDDR6X Memory, 420W TBP, 35% Faster Than RTX 3090 Ti

The clock speeds should not confirmed but however contemplating that the TSMC 4N course of is getting used, we expect clocks between the two.0-3.0 GHz vary. The greater than common clock velocity bump comes from the truth that NVIDIA is making a two-node bounce contemplating the Ampere GPUs with Samsung 8nm node was in actuality a 10nm course of node with some optimizations. NVIDIA is skipping 7nm and going straight for a 5nm node and never even the vanilla variant however an optimized model of it. With Pascal on the TSMC 16nm node, NVIDIA delivered an enormous frequency leap and we are able to count on an analogous bounce this time round too.




2 of 9

As for reminiscence specs, the GeForce RTX 4080 is anticipated to rock 16 GB GDDR6X capacities which might be stated to be adjusted at 21 Gbps speeds throughout a 256-bit bus interface. This will present as much as 672 GB/s of bandwidth. For energy, the TBP is claimed to be rated at round 420W which is near the RTX 4090 and for the reason that reminiscence clocks aren’t that aggressive, it’s seemingly that the core clocks could possibly be tuned for max graphics efficiency.

In phrases of efficiency, the NVIDIA GeForce RTX 4080 is anticipated to supply 15,000 factors within the 3DMark Time Spy benchmark which the leaker had beforehand said as a conservative determine so one can count on round a 35% efficiency uplift over the RTX 3090 Ti on this particular benchmark.







As for its function set, the NVIDIA GeForce RTX 4080 graphics playing cards will rock all the trendy NV function units akin to the most recent 4th Gen Tensor Cores, third gen RT cores, the most recent NVENC Encoder, and NVCDEC Decoder, and assist for the most recent APIs. They will pack all the trendy RTX options akin to DLSS, Reflex, Broadcast, Resizable-BAR, Freestyle, Ansel, Highlights, Shadowplay, and G-SYNC assist too. The graphics card ought to launch round This fall 2022 or might even slip too Q1 ’23 but it surely ought to come priced at round $699-$799 US.

NVIDIA GeForce RTX 4080 Series Preliminary Specs:

Graphics Card Name NVIDIA GeForce RTX 4080 Ti NVIDIA GeForce RTX 4080 NVIDIA GeForce RTX 3090 Ti NVIDIA GeForce RTX 3080
GPU Name Ada Lovelace AD103-350? Ada Lovelace AD103-300? Ampere GA102-225 Ampere GA102-200
Process Node TSMC 4N TSMC 4N Samsung 8nm Samsung 8nm
Die Size ~450mm2 ~450mm2 628.4mm2 628.4mm2
Transistors TBD TBD 28 Billion 28 Billion
CUDA Cores 10752? 9728? 10240 8704
TMUs / ROPs TBD / 224? TBD / 214? 320 / 112 272 / 96
Tensor / RT Cores TBD / TBD TBD / TBD 320 / 80 272 / 68
Base Clock TBD TBD 1365 MHz 1440 MHz
Boost Clock ~2600 MHz ~2500 MHz 1665 MHz 1710 MHz
FP32 Compute ~55TFLOPs ~50 TFLOPs 34 TFLOPs 30 TFLOPs
Tensor-TOPs TBD TBD 273 TOPs 238 TOPs
Memory Capacity 16 GB GDDR6X 16 GB GDDR6X 12 GB GDDR6X 10 GB GDDR6X
Memory Bus 256-bit 256-bit 384-bit 320-bit
Memory Speed 24.0 Gbps? 21.0 Gbps? 19 Gbps 19 Gbps
Bandwidth 768 GB/s 672 2GB/s 912 Gbps 760 Gbps
TGP 450W 420W 350W 320W
Price (MSRP / FE) $1199 US? $699 US? $1199 $699 US
Launch (Availability) 2022? July 2022? third June 2021 seventeenth September 2020

Products talked about on this put up