AMD confirms that MI300X GPU TBP is 750W

Thanks to CTOnews.com netizens Xiao Zhan cut, South China Daniel Wu's clue delivery! CTOnews.com June 16, AMD unveiled the latest Instinct MI300X GPU at the data center and AI technology premiere on Tuesday. AMD did not disclose many details in the keynote speech, and Hoang Anh Phu later found that the MI300X (192 GB HBM3,OAM module) TBP is 750W, compared with 500W-560W for the previous generation MI250X TBP.

CTOnews.com previously reported that MI300X is a pure GPU version that uses AMD CDNA 3 technology and uses up to 192 GB of HBM3 high-bandwidth memory to accelerate large language models and generative AI computing.

MI300X and its CDNA architecture are designed for large language models and other advanced AI models, encapsulating 12 5nm chiplets together for a total of 153 billion transistors.

This new AI chip abandons APU's 24 Zen cores and I / O chips in favor of more CDNA 3 GPU and larger 192GB HBM3, providing 5.2TB / s memory bandwidth and unlimited 896GB/s bandwidth.

Related readings:

"with 153 billion transistors, AMD throws out the strongest AI chip, and a single GPU runs a big model."