NVIDIA RTX 4070 clock speeds to be higher than RTX 4090

The RTX 40 series are going through the last stage of development, which also means changes to the specs.

Following a major spec update for RTX 4070 SKU, which increased CUDA core spec to 7680 and memory to 12GB capacity, there is also an update to the clock speeds. First we’ve learned the memory speed is not 18 Gbps, which would imply GDDR6 memory, but 21 Gbps which is GDDR6X spec. Higher capacity and higher memory means a significant increase in bandwidth compared to old specs, which is now at 504 GB/s.

Today hardware leaker Kopite7kimi clarifies the situation for the GPU clocks. The same leaker already revealed the full specs for the RTX 4090 flagship Ada GPU, therefore we can now compare two models from the new series. Overall, the GPU clock is 70 to 90 MHz higher than the 450W model. The RTX 4070 reportedly has a base clock of 2310 MHz and a boost of 2610 MHz. Since NVIDIA’s official boost clock is always lower than real-world clock, Kopite also confirms that the maximum boost should exceed 2.8 GHz.

Long story short, we are looking at a major clock speed update for RTX 40 series. The RTX 3070 had 700-900 MHz lower clocks. Higher clocks in combination with more cores will enable 40 TFLOPS of compute power (based on official boost clock figure). That’s 2x the compute power of RTX 3070, or alternatively the same compute power as RTX 3090 Ti (40 TFLOPS).

The RTX 4070 appears to be designed to offer half the performance and half the memory of the RTX 4090 SKU. The only thing not scaling the same way is the power consumption. The RTX 4070 has a rumored total board of 285W, an increase by 45W over RTX 3070. Do note that’s not TDP, but a board limit.

While all high-end RTX 40 cards are to be announced at the same time, one should expect RTX 4070 to launch after RTX 4090 and RTX 4080 so most likely in the middle of the fourth quarter this year.

Source: @Kopite7kimi