The week is starting off well with the next-gen NVIDIA Ada Lovelace GPU rumor mill, with leaker "kopite7kimi" teasing the continuously updating rumored specs of NVIDIA's upcoming GeForce RTX 40 series graphics cards.
NVIDIA's new flagship GeForce RTX 4090 graphics card has a little more details from kopite7kimi, with the AD102-300-1 GPU clocking at over 2.75GHz. The leaker says that we can expect a 2235MHz base GPU clock, 2520MHz boost GPU clock, and 2750MHz "actual max" GPU clock. Impressive, very impressive... considering 2250MHz is about the limit for the GeForce RTX 3090 Ti outside of insane LN2 cooling and mods for days.
If we're expecting "actual max" GPU clocks of 2.75GHz then we could see custom GeForce RTX 4090 graphics cards from the likes of ASUS and MSI to reach 2.8GHz and above... while the heights of 3.0GHz+ on an NVIDIA GPU would be awesome to see.
- Read more: NVIDIA GeForce RTX 4090 Founders Edition teased with triple-fan cooler
- Read more: NVIDIA GeForce RTX 4090, 4080, 4070: new rumored specs are here
- Read more: NVIDIA AD102 GPU for GeForce RTX 4090 Ti: power limits of 800W
The Ada Lovelace-based NVIDIA AD102-300-1 GPU would be joined by 24GB of GDDR6X memory clocked at 21Gbps, which is the same as the previous rumor. No change there with the ultra-fast GDDR6X memory, but some more information on the GPU clocks... the tease of 2.75GHz+ is very nice to hear. Exciting times... and 'just' 450W of power to do it.
GeForce RTX 4090 (very latest rumored specs)
- GPU: AD102-300
- GPU clocks: base 2235, boost 2520, actual max 2750+
- CUDA cores: 16384 (up from 16128)
- SMs: 128 (up from 126)
- VRAM: 24GB GDDR6X @ 21Gbps
- Memory bus: 384-bit
- TDP: 450W or so
- Read more: AIBs 'preparing 4.5-slot coolers' for an 'undisclosed' NVIDIA GPU
- Read more: NVIDIA's next-gen GeForce RTX 4090: AD102 could push 100 TFLOPs+
- Read more: NVIDIA testing insane next-gen AD102 GPU: freaking 900W power!!!
- Read more: NVIDIA's new AD102-based GeForce RTX 4090: 600W+ power usage CONFIRMED
- Read more: NVIDIA GeForce RTX 4090: actually OVER twice as fast as the RTX 3090
- Read more: NVIDIA GeForce RTX 4090 rumor: August launch, RTX 4080 in September
The last we heard about the chunky coolers for Ada Lovelace GPUs in the GeForce RTX 40 series family was also from Moore's Law is Dead, where his sources said that "AIBs are preparing 4.5-slot coolers right now for some undisclosed NVIDIA product. Already case-makers are adjusting their designs to support these monsters".
So if we have AD102-300-A1 GPUs ticking at over 2.75GHz and going north of 2.9GHz, those monster 4.5-slot designs make sense. NVIDIA is putting the pedal to the metal when it comes to Ada Lovelace GPU clocks in near-full-fat AD102-300 form... as it needs to compete against AMD's upcoming RDNA 3-based Navi 31-powered Radeon RX 7970 XT graphics card.
GeForce RTX 4090 (new rumored specs +GPU clocks)
- GPU: AD102-300
- GPU clocks: base 2235, boost 2520, actual max 2750+
- CUDA cores: 16384 (up from 16128)
- SMs: 128 (up from 126)
- VRAM: 24GB GDDR6X @ 21Gbps
- Memory bus: 384-bit
- TDP: 450W or so
GeForce RTX 4080 (new rumored specs)
- GPU: AD103-300-A1
- CUDA cores: 10240
- SMs: 80
- VRAM: 16GB GDDR6 @ 18Gbps
- Memory bus: 256-bit
- TDP: 420W or so
GeForce RTX 4070 (new rumored specs)
- GPU: AD102-275 (used to be AD104-400)
- CUDA cores: 7168
- SMs: 56
- VRAM: 12GB GDDR6 (up from 10GB GDDR6) @ 18Gbps
- Memory bus: 192-bit (up from 160-bit)
- TDP: 300W or so