Overclock.net banner

[Official] NVIDIA RTX 4090 Owner's Club

1 reading
2.3M views 21K replies 914 participants last post by  HoBahr  
#1 · (Edited)
Last Updated: January 22, 2023

Note: This content is licensed under Creative Commons 3.0. This means that you are free to copy and redistribute this material, but only if the following criteria are met: 1) You must give appropriate credit by linking back to this thread. 2) You may not use this material for commercial purposes or place this on a for-profit website with ads. 3) You cannot create derivative work based on this material.

NVIDIA GeForce® RTX 4090


⠀⠀RTX 4080 Owner's Club
→ RTX 4090 Owner's Club


Click here to join the discussion on Discord or join directly through the Discord app with the code kkuFR3d

Image

Source: NVIDIA

SPECS (Click Spoiler)

Rich (BB code):
 
   Architecture Ada Lovelace
   Chip AD102-300
   Transistors 76,300 million
   Die Size 608 mm²
   Manufacturing Process 4nm

   CUDA Cores 8192 (16384)
   TMUs 512
   ROPs 176
   SM Count 128
   Tensor Cores 512
   GigaRays -- GR/s

   Core Clock 2230 MHz
   Boost Clock 2520 MHz
   Memory 24GB GDDR6X
   Memory Bus 384-bit
   Memory Clock 1313 MHz / 21008 MHz
   Memory Bandwidth 1008 GB/s
   External Power Supply 12-Pin
   TDP 450W

   DirectX 12.2 Ultimate
   OpenGL 4.6
   OpenCL 3.0
   Vulkan 1.3
   CUDA 8.9

   Interface PCIe 4.0 x16
   Connectors 1x HDMI 2.1, 3x DisplayPort 1.4a
   Dimensions 304 x 137mm (3-Slot)

   Price $1599 US

   Release Date October 12, 2022

Rich (BB code):
RTX 4090    | AD102-300 |  4nm | 608mm² | 76.3 BT | 16384 CCs | 512 TMUs | 176 ROPs | 128 SMs | 2520 MHz |  24GB | 2048MB x 12 | GDDR6X | 384-bit | 1008 GB/s | 450W⠀⠀
RTX 4080    | AD103-300 |  4nm | 379mm² | 45.9 BT |⠀ 9728 CCs | 304 TMUs | 112 ROPs | ⠀76 SMs | 2505 MHz |  16GB | 2048MB x 8  | GDDR6X | 256-bit | ⠀716 GB/s | 320W⠀⠀
RTX 3090 Ti | GA102-350 |  8nm | 628mm² | 28.3 BT | 10752 CCs | 336 TMUs | 112 ROPs | ⠀84 SMs | 1865 MHz |  24GB | 2048MB x 12 | GDDR6X | 384-bit | 1008 GB/s | 450W⠀⠀
RTX 3090    | GA102-300 |  8nm | 628mm² | 28.3 BT | 10496 CCs | 328 TMUs | 112 ROPs | ⠀82 SMs | 1695 MHz |  24GB | 1024MB x 24 | GDDR6X | 384-bit | ⠀936 GB/s | 350W⠀⠀
RTX 3080 Ti | GA102-250 |  8nm | 628mm² | 28.3 BT | 10240 CCs | 320 TMUs | 112 ROPs | ⠀80 SMs | 1665 MHz |  12GB | 1024MB x 12 | GDDR6X | 384-bit | ⠀912 GB/s | 320W⠀⠀
RTX 3080    | GA102-200 |  8nm | 628mm² | 28.3 BT |⠀ 8704 CCs | 272 TMUs |  96 ROPs | ⠀68 SMs | 1710 MHz |  10GB | 1024MB x 10 | GDDR6X | 320-bit | ⠀760 GB/s | 320W
Note: Gaming performance on Ampere and later, do not scale linearly with CUDA core count when compared with previous generations.
Rich (BB code):
RTX 2080 Ti | TU102-300 | 12nm | 754mm² | 18.6 BT |⠀ 4352 CCs  | 272 TMUs |  88 ROPs | ⠀68 SMs | 1635 MHz |  11GB | 1024MB x 11 | GDDR6  | 352-bit | ⠀616 GB/s | 250W
RTX 2080 S  | TU104-450 | 12nm | 545mm² | 13.6 BT |⠀ 3072 CCs  | 192 TMUs |  64 ROPs | ⠀48 SMs | 1815 MHz |   8GB | 1024MB x 8  | GDDR6  | 256-bit | ⠀496 GB/s | 250W
RTX 2080    | TU104-400 | 12nm | 545mm² | 13.6 BT |⠀ 2944 CCs  | 184 TMUs |  64 ROPs | ⠀46 SMs | 1710 MHz |   8GB | 1024MB x 8  | GDDR6  | 256-bit | ⠀448 GB/s | 215W
GTX 1080 Ti | GP102-350 | 16nm | 471mm² | 12.0 BT |⠀ 3584 CCs  | 224 TMUs |  88 ROPs | ⠀28 SMs | 1582 MHz |  11GB | 1024MB x 11 | GDDR5X | 352-bit | ⠀484 GB/s | 250W
GTX 1080    | GP104-400 | 16nm | 314mm² |  7.2 BT | ⠀2560 CCs  | 160 TMUs |  64 ROPs | ⠀20 SMs | 1733 MHz |   8GB | 1024MB x 8  | GDDR5X | 256-bit | ⠀320 GB/s | 180W
GTX 980 Ti  | GM200-310 | 28nm | 601mm² |  8.0 BT |⠀ 2816 CCs  | 172 TMUs |  96 ROPs | ⠀22 SMs | 1076 MHz |   6GB |  512MB x 12 | GDDR5  | 384-bit | ⠀336 GB/s | 250W
GTX 980     | GM204-400 | 28nm | 398mm² |  5.2 BT |⠀ 2048 CCs  | 128 TMUs |  64 ROPs | ⠀16 SMs | 1216 MHz |   4GB |  512MB x 8  | GDDR5  | 256-bit | ⠀224 GB/s | 165W
GTX 780 Ti  | GK110-425 | 28nm | 551mm² |  7.1 BT |⠀ 2880 CCs  | 240 TMUs |  48 ROPs | ⠀15 SMs |  928 MHz |   3GB |  256MB x 12 | GDDR5  | 384-bit |⠀ 336 GB/s | 250W
GTX 780     | GK110-300 | 28nm | 551mm² |  7.1 BT | ⠀2304 CCs  | 192 TMUs |  48 ROPs | ⠀12 SMs |  900 MHz |   3GB |  256MB x 12 | GDDR5  | 384-bit |⠀ 288 GB/s | 250W
GTX 680     | GK104-400 | 28nm | 294mm² |  3.5 BT |⠀ 1536 CCs  | 128 TMUs |  32 ROPs |  ⠀8 SMs | 1058 MHz |   2GB |  256MB x 8  | GDDR5  | 256-bit | ⠀192 GB/s | 200W
GTX 580     | GF110-375 | 40nm | 520mm² |  3.0 BT |  ⠀512 CCs  |  64 TMUs |  48 ROPs | ⠀16 SMs |  772 MHz | 1.5GB |  128MB x 12 | GDDR5  | 384-bit | ⠀192 GB/s | 250W

ASUS
AsusTek Computer (stylised as ASUS) was founded in Taipei, Taiwan in 1989, currently headquartered in Taipei, Taiwan.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
Strix OC358mm3.50322500/600WCustomMP298124Ă—70A (1680A) FDMF31704Ă—70A (280A) FDMF317090YV0ID0-M0NA00
TUF OC349mm3.65322450/600WCustomMP2888A18Ă—70A (1260A) TDA215704Ă—50A (200A) SIC63990YV0IE0-M0NA00

COLORFUL - Not available in Europe or North America
Colorful Group (referred to as CFG) was founded in Shenzhen, China in 1995, currently headquartered in Shenzhen, China.


ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
Neptune OC254mm2.00AIO12550/630WCustomuP9512U24Ă—55A (1320A) AOZ5311NQI-034Ă—55A (220A) AOZ5311NQI-03N/A
Vulcan OC349mm3.50312515/550WCustomuP9512U24Ă—55A (1320A) AOZ5311NQI-034Ă—55A (220A) AOZ5311NQI-03N/A
NB EX327mm3.35311450/480WReferenceuP9512U14Ă—55A (770A) AOZ5311NQI-033Ă—55A (165A) AOZ5311NQI-03N/A

EVGA
EVGA Corporation was founded in California, United States in 1989, currently headquartered in California, United States.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
FTW3 Ultra318mm3.65312500W/600WCustomuP9512U24Ă—50A (1200A) SiC653A4Ă—50A (200A) SiC653APrototype

GALAX | KFA2 - Not available in North America
GALAXY was founded in Hong Kong, China in 1994, GALAXY and its European brand KFA2 (Kick Friggin Ass) merged in 2014 to form GALAX as a single unified brand, the name KFA2 still exist for the European market but all designs are GALAX, currently headquartered in Hong Kong, China.


ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
HOF344mm3.85312550/666WCustomXDPE10281B28Ă—70A (1960A) TDA215704Ă—70A (280A) TDA2157049NXM5MD6PHE
HOF344mm3.85312550/666WCustomXDPE10281B28Ă—70A (1960A) TDA215704Ă—70A (280A) TDA2157049NXM5MD6PHE
SG336mm3.70311450/510WReferenceuP9512U18Ă—50A (900A) NCP3021504Ă—50A (200A) NCP30215049NXM5MD6DSG
SG336mm3.70311450/510WReferenceuP9512U18Ă—50A (900A) NCP3021504Ă—50A (200A) NCP30215049NXM5MD6DSK

GIGABYTE
GIGA-BYTE Technology (stylised as GIGABYTE) was founded in Taipei, Taiwan in 1986, currently headquartered in Taipei, Taiwan and California, United States.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
Xtreme Waterforce238mm2.00AIO12450/600WCustomuP9512U24Ă—50A (1200A) SiC653A4Ă—50A (200A) SiC653AGV-N4090AORUSX W-24GD
Master359mm3.75312450/600WCustomuP9512U24Ă—50A (1200A) SiC653A4Ă—50A (200A) SiC653AGV-N4090AORUS M-24GD
Gaming OC340mm3.75312450/600WCustomuP9512U20Ă—50A (1000A) SiC653A4Ă—50A (200A) SiC653AGV-N4090GAMING OC-24GD
Windforce331mm3.50312450/480WCustomuP9512U14Ă—50A (700A) SiC653A4Ă—50A (200A) SiC653AGV-N4090WF3-24GD

INNO3D
InnoVISION Multimedia was founded in Hong Kong, China in 1989, primarily recognized for its graphic cards marketed under the Inno3D brand, acquired by PC Partner in 2008, currently headquartered in Hong Kong, China.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
iCHILL Frostbite200mm2.00Water11450/450WReferenceuP9512U14Ă—55A (770A) AOZ5311NQI3Ă—55A (165A) AOZ5311NQIC4090-246XX-1833FB
iCHILL Black280mm2.00AIO11450/450WReferenceuP9512U14Ă—55A (770A) AOZ5311NQI3Ă—55A (165A) AOZ5311NQIC4090-246XX-18330005
iCHILL X3334mm3.00311450/450WReferenceuP9512U14Ă—55A (770A) AOZ5311NQI3Ă—55A (165A) AOZ5311NQIC40903-246XX-1833VA47
X3 OC336mm3.0311450/450WReferenceuP9512U14Ă—55A (770A) AOZ5311NQI3Ă—55A (165A) AOZ5311NQIN40903-246XX-18332989

MSI
Micro-Star International (stylised MSI) was founded in Taipei, Taiwan in 1986, currently headquartered in Taipei, Taiwan.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
Suprim Liquid X280mm2.15AIO12480/600WCustomMP298126Ă—70A (1820A) MP869574Ă—70A (280A) MP86957V510-007R
Suprim X336mm3.90312480/520WCustomMP298126Ă—70A (1820A) MP869574Ă—70A (280A) MP86957V510-001R
Gaming X Trio337mm3.85312450/480WCustomMP298118Ă—50A (900A) NCP303151A4Ă—50A (200A) NCP303151AV510-006R
Ventus OC322mm3.10311450/450WV510-023R

NVIDIA
Nvidia Corporation (stylised nVIDIA) was founded in California, United States in 1993, currently headquartered in California, United States.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
Founders Edition304mm3.05211450/600WCustomMP298120Ă—70A (1400A) MP869573Ă—70A (210A) MP86957900-1G136-2530-000

PALIT | GAINWARD - Not available in North America
Palit Microsystems (stylised PaLiT) was founded in Taipei, Taiwan in 1988, acquired the Gainward brand and company in 2005, currently headquartered in Taipei, Taiwan.


ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
GameRock OC330mm3.60312450/500WCustomuP9512U16Ă—50A (800A) NCP3021503Ă—50A (150A) NCP302150NED4090S19SB-1020G
Phantom GS330mm3.50312450/500WCustomuP9512U16Ă—50A (800A) NCP3021503Ă—50A (150A) NCP302150NED4090S19SB-1020P

PNY
PNY Technologies was founded in New York, United States in 1985, currently headquartered in New Jersey, United States.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
XLR8 OC332mm3.55311450/450WCustomuP9512U14Ă—50A (700A) NCP3021503Ă—50A (150A) NCP302150VCG409024TFXXPB1-O
Uprising351mm3.15311450/450WCustomuP9512U14Ă—50A (700A) NCP3021503Ă—50A (150A) NCP302150VCG409024TFXMPB
Verto337mm2.95311450/450WCustomuP9512U14Ă—50A (700A) NCP3021503Ă—50A (150A) NCP302150VCG409024TFXPB1

ZOTAC
ZOTAC is under the umbrella of PC Partner, and was founded in Hong Kong, China in 2006, currently headquartered in Hong Kong, China.

ModelLengthSlotFanHDMIBIOSPower LimitPCBPWMGPU StageVRAM StageMPN
AMP Extreme356mm3.60312450/495WCustomuP9512U24Ă—55A (1320A) AOZ5311NQI-034Ă—55A (220A) AOZ5311NQIZT-D40900B-10P
Trinity OC356mm3.60312450/495WCustomuP9512U14Ă—55A (770A) AOZ5311NQI-034Ă—55A (220A) AOZ5311NQIZT-D40900J-10P

TECHPOWERUP | GPU-Z

Download TechPowerUp GPU-Z

NVIDIA | NVFLASH

Download NVIDIA NVFlash

BIOS | ROM

TechPowerUp BIOS Collection < Verified

TechPowerUp BIOS Collection < Unverified

OVERCLOCKING | TOOLS

Download ASUS GPUTweak III

Download Colorful iGame Center

Download Gainward EXPERTool

Download Galax/KFA2 Xtreme Tuner Plus

Download Gigabyte AORUS Engine

Download Inno3D TuneIT

Download MSI Afterburner

Download Palit ThunderMaster

Download PNY Velocity X

Download Zotac FireStorm
 
#3 ·
 
#5 ·
Please loan me 3 large so I can join this club.
 
#7 ·
gg
Image
 
#9 ·
Gonna be good for watercoolers because waterblockers don't care about the dick-extension 6" of heatsink hanging off the end of the PCB. So relatively short PCB.

Strix I'm betting on like 550W or something. They can't go over 600? on the single connector and we don't have EVGA anymore to put out 1000W bios.
 
#10 ·
Gonna be good for watercoolers because waterblockers don't care about the dick-extension 6" of heatsink hanging off the end of the PCB. So relatively short PCB.

Strix I'm betting on like 550W or something. They can't go over 600? on the single connector and we don't have EVGA anymore to put out 1000W bios.
Galax might help us out with a 1000w, but it might be 2 connector. Asus usually has one as well I think.
 
#12 ·
It’s kinda funny, because while I have owned my 3090KP HC for a long while now. It still feels super freaking powerful to this day. It is OCed to the absolute max.

The 4090 better be a worth while upgrade. Just saying.
 
  • Rep+
Reactions: 645680
#13 ·
It’s kinda funny, because while I have owned my 3090KP HC for a long while now. It still feels super freaking powerful to this day. It is OCed to the absolute max.
The 3000 series generally sucked for overclocking with KPE being the same overclocks as anything else. Core clock -> 2200 or 2250 tops. I guess memory overclocks were decent but FPS didn't really care so much.
 
#14 ·
The 3000 series generally sucked for overclocking with KPE being the same overclocks as anything else. Core clock -> 2200 or 2250 tops. I guess memory overclocks were decent but FPS didn't really care so much.
I'd be happy to get my power draw from a screaming, overclocked, 600+ watt 3090 to a "meager" 450W.
 
#15 ·
Hope you all been bless!

Wildness for now. Since there’s no more KP to speak of, I’m guessing HOF will be the only gpu with software voltage control out the box.

Lets hope that Strix (or any other high end 4090) still has an I2C header this time round for some EVC.

Look forward to pcb shots.
 
#16 ·
Lets hope that Strix (or any other high end 4090) still has an I2C header this time round for some EVC.
Step 1 though will be voltage actually mattering. The 3090 didn't benefit at all from more voltage (except maybe under LN2). I had the I2C header soldered on my TUF.
 
#18 · (Edited)
Step 1 though will be voltage actually mattering. The 3090 didn't benefit at all from more voltage (except maybe under LN2). I had the I2C header soldered on my TUF.

I think we took different steps lol. I broke highest non ln2 Port Royal (at time of bench) and am still 11th globally.

Voltage absolutely matters, maybe on air or normal water it does little, but from my experience it did.

TUF wasn’t a great card, that i2c header was basically useless unless on a good bin Strix.

But I absolutely agree that adding voltage has been getting less effective with each series.

Image
 
#19 ·
I think we took different steps lol. I broke highest non ln2 Port Royal (at time of bench) and am still 11th globally.

Voltage absolutely matters, maybe on air or normal water it does little, but from my experience it did.

TUF wasn’t a great card, that i2c header was basically useless unless on a good bin Strix.

But I absolutely agree that adding voltage is getting less effective with each series.

...are you sure you're not running low on Primoflex tubing ? o_O

Also, I would love to see Asus (re)introduce the Matrix series, so Galax HoF doesn't feel so lonely with KPE in detention
 
#20 ·
The 3000 series generally sucked for overclocking with KPE being the same overclocks as anything else. Core clock -> 2200 or 2250 tops. I guess memory overclocks were decent but FPS didn't really care so much.
How I have my 3090KP set up it’s 18% faster than a 3090FE. That’s a great in my book. While you could get other 3090’s to do this you’ll spend the same or even more than a 3090KP cost.

The 3090KP was a great card because right out of the box you had your 520 watts available. 1995Mhz Bin written on the die, good memory. And at just default speeds, it puts out more Tflops than a 3090Ti FE.

But, enough is enough! I’ve enjoyed it so much. I’m looking forward to the RTX4000 series.
 
  • Rep+
Reactions: GRABibus and 645680