NVIDIA GeForce RTX 4070 non-Ti rumored to have 2475 MHz GPU boost clock – VideoCardz.com

Please note that this post is tagged as a rumor.

First GeForce RTX 4070 already being tested

Matthew Smith, a TechPowerUP GPU database maintainer, claims that some RTX 4070 cards already have the confirmed clock speeds.

Colorful is the first company to submit a factory-overclocked RTX 4070 non-Ti graphics card to GPU-Z validation database, which we believe is the source of this information. This means that the card is already running in the labs, and it is now being tested with non-standard clocks.

The RTX 4070 reportedly has a 1920 MHz base clock and 2475 MHz boost clock. Compared to RTX 4070 Ti that is 135 MHz lower boost and 390 MHz lower base. Furthermore, Colorful’s RTX 4070 iGame Ultra White OC is said to have a boost clock of 2505 MHz, which represents a 30 MHz overclock.

Reference RTX 4070 has a Base clock of 1920 and 2475 boost

first AIB to finish a 4070 is Colorful with their Ultra W OC line, boost of 2505 MHz

— Matthew Smith ᅠ (@T4CFantasy) January 30, 2023

Matthew also weighs in to the recent TITAN ADA rumors. This card is now confirmed to exist but no one knows when and if NVIDIA will actually launch it. On the other hand, the new TITAN has already appeared in the validation database as well with clock speeds of 2235 MHz and 2520 MHz for base and boost respectively (same clocks as RTX 4090). Additionally, he confirms that this model has 48GB of GDDR6X memory.

The RTX 4070 non-Ti graphics card is reportedly entering mass production in February, likely to be followed by RTX 4060 Ti later. NVIDIA has not yet confirmed when both cards would be released, but both Ada AD104 and AD106 GPUs are or will be present on the market soon (mid-range RTX 40 mobile series launch on February 22nd).

RUMORED NVIDIA GeForce RTX 40 Series Specs
VideoCardz.com	RTX 4070 Ti	RTX 4070	RTX 4060 Ti
Picture
Board-SKU	PG141-SKU331	PG141-SKU336/337	PG190
Architecture	Ada (TSMC 4N)	Ada (TSMC 4N)	Ada (TSMC 4N)
GPU	AD104-400	AD104-250/251	AD106-350
CUDA Cores
Base Clock	2310 MHz	1920 MHz	TBC
Boost Clock	2610 MHz	2475 MHz	TBC
Max FP32 Compute	40 TFLOPS	29 TFLOPS	TBC
Memory	12 GB G6X	12 GB G6X	8 GB G6
Memory Bus	192-bit	192-bit	128-bit
Memory Bandwidth	504 GB/s	504 GB/s	288 GB/s
Default TGP
Release Date	January 5th, 2023	Q1 2023 (?)	Q1 2023 (?)

Source: Matthew Smith