Sunday, April 16th 2023
Colorful Custom RTX 4060 Ti GPU Clocks Outed, 8 GB VRAM Confirmed
Resident TechPowerUp hardware database overseer T4C Fantasy has divulged some early information about a custom version of the NVIDIA GeForce RTX 4060 Ti GPU card - Colorful's catchily named iGame RTX 4060 Ti Ultra White OC model has been added to the TPU GPU database, and T4C Fantasy has revealed a couple of tidbits on Twitter. The GPU has been tuned to have a maximum boost clock of 2580 MHz, jumping from a base clock of 2310 MHz. According to past leaks the reference version of the GeForce RTX 4060 Ti has a default boost clock of 2535 MHz, so Colorful's engineers have managed to add another 45 MHz on top of that with their custom iteration - so roughly 2% more than the reference default.
T4C Fantasy also confirmed that the Colorful iGame RTX 4060 Ti Ultra W OC will be appointed with 8 GB of VRAM, which also matches the reference model's rumored memory spec. T4C Fantasy points out that brands have the option to produce RTX 4060 Ti cards with a larger pool of attached video memory, but launch models will likely stick with the standard allotment of 8 GB of VRAM. The RTX 4060 Ti is listed as being based on the Ada Lovelace GPU architecture (GPU variant AD106-350-A1), and T4C Fantasy expects that Team Green will stick with a 5 nm process size - contrary to reports of a transition to manufacturing on 4 nm (chez TSMC foundries).
Sources:
T4C Fantasy Tweet 1, T4C Fantasy Tweet 2
T4C Fantasy also confirmed that the Colorful iGame RTX 4060 Ti Ultra W OC will be appointed with 8 GB of VRAM, which also matches the reference model's rumored memory spec. T4C Fantasy points out that brands have the option to produce RTX 4060 Ti cards with a larger pool of attached video memory, but launch models will likely stick with the standard allotment of 8 GB of VRAM. The RTX 4060 Ti is listed as being based on the Ada Lovelace GPU architecture (GPU variant AD106-350-A1), and T4C Fantasy expects that Team Green will stick with a 5 nm process size - contrary to reports of a transition to manufacturing on 4 nm (chez TSMC foundries).
44 Comments on Colorful Custom RTX 4060 Ti GPU Clocks Outed, 8 GB VRAM Confirmed
You're not wrong though. Nvidia will push games people don't play with settings people don't use to clog the media with "nvidia wins" content.
Meanwhile, 95%+ of the target audience are playing games that don't have DLSS3, or RT, or both.
Jensen: "The joke is when they sell and I'm the only one laughing."
Lisa: "What he said."
Tom: "You could not though."
Jensen: "But they will."
Lisa: "What he said."
Graphics don't make the game good, and scaling up screen texture quality is meaningless if the scene is optimised for a lower resolution and poly-count.
This shrinking bus will continue with vengeance with Blackwell as Nvidia is paying so much for TSMC's 3nm they are forced to make dies as small as possible. I wouldn't be surprised to see 5080 on 192bit, 5070Ti on 160 bit, 5070 on 128 bit and 4060 on 96 bit. They will claim DDR7 will give them all the bandwidth they need. and hammer fake frames tech to make passable performance at ultra settings.
8GB is the new 4GB. Even the 12GB of the 4070 Ti are a joke for the money.
RTX 2080 ti has FP32 (float) 13.45 TFLOPS. Vs. 82,58 TFLOPS of RTX 4090. In term of FPS RTX 4090 must have 6.15X more FPS than RTX 2080 ti...
TOPS = Tera "trillion" Operations Per Second or TeraOPS.
For the Ampere generation, the discrete TIOPS CUDA cores gained floating point processing capability. RTX 3070 Ti has 21.75 TFLOPS.
Pure TFLOPS argument between Turing vs Ampere hides Turing's discrete TIOPS CUDA cores.
In terms of CUDA TOPS capability, RTX 2080 Ti is close to RTX 3070 Ti / RTX 3070.PS5 has 256-bit 16 GB GDDR6-14000 and 512 MB DDR4.
XSX has 320-bit 16 GB GDDR6-14000.
Nvidia says gamepass only needs 8gb as long as it's a rt card :p
If no "decent" competition shows up, they'll never bother.