News Gigabyte EEC Listing Confirms AMD RX 7600, Nvidia RTX 4060 Ti Cards for Launch

[Admin]

A filling from Gigabyte with the EEC confirmed the company is gearing up to launch eleven different graphics card models, including two variations of AMD's upcoming RX 7600 8GB and Nvidia RTX 4060 Ti 8GB.

Gigabyte EEC Listing Confirms AMD RX 7600, Nvidia RTX 4060 Ti Cards for Launch : Read more

 

[peachpuff]

8gb for every body! Thanks amd 🙄

 

[Metal Messiah.]

Based on current leaks, the RX 7600 will supposedly have 28 RDNA3 Compute Units. That's the same count as the existing RX 6600, but with architectural enhancements that should further boost performance.

Are you sure about this ?

Because as far as I know, The Navi 33 GCD is expected to feature 2 Shader Engines and each Shader Engine has 2 Shader Arrays (2 per SE / 4 in total). Seen the block diagram. So based on this info, we get 16 WGP's or 32 Compute Units for a total of 2048 cores which is the same core count as the Navi 23 GPU.

• AMD Navi 33: 2048 Cores, 128-bit Bus, 32 MB Infinity Cache, 204mm2 GPU Die @6nm
• AMD Navi 23: 2048 Cores, 128-bit Bus, 32 MB Infinity Cache, 237mm2 GPU Die @7nm

Obviously, the GPU will also come packaged with 32 MB of Infinity Cache, the same amount as the Navi 23 GPU, and across a 128-bit wide bus.

 

[oofdragon]

Rumours 2022: 7900XT will be twice as fast as a Rtx4090
Retailers 2023: 7600 can't even compete with a 6700

 

[oofdragon]

Hey I have a question that I didn't see ANY tech site covering.. why is the RTX4000 made on 4nm technology but the RX7000 on 6nm??? AMD lost a whole gen going this route

 

[AgentBirdnest]

Hey I have a question that I didn't see ANY tech site covering.. why is the RTX4000 made on 4nm technology but the RX7000 on 6nm??? AMD lost a whole gen going this route

Only the small Memory Cache Dies are 6nm (because cache doesn't benefit much from 5nm. The GPD/Graphics Compute Die is 5nm.
"4N" is a special version of TSMC's 5nm, tweaked for Nvidia. It's probably not much more dense than regular 5nm. So the density between AMD and Nvidia is probably pretty close.

Don't forget that last gen, AMD used TSMC 7nm, and Nvidia used Samsung 8nm (which was closer to TSMC's 10nm in density.) And Nvidia did pretty well, if I recall. : P

 

[healthy Pro-teen]

Rumours 2022: 7900XT will be twice as fast as a Rtx4090
Retailers 2023: 7600 can't even compete with a 6700

source?