⁶ Source for Nvidia H100 LLAMA2-70B performance https://developer.nvidia.com/deep-learning-performance-training-inference/training, April 29, 2024, a “Large Language Model” tab.​
Intel Gaudi 3 measurements and projections by Habana Labs, April 2024; Results may vary​

⁷ Source for Nvidia performance: Overview — tensorrt_llm documentation (nvidia.github.io), May, 2024. Reported numbers are per GPU.​
Intel Gaudi 3 projections by Habana Labs, April 2024; Results may vary​

⁸ Based on total number of platform Tops on Lunar Lake vs. prior generation.

© Intel Corporation. Intel, the Intel logo and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.

View source version on businesswire.com: https://www.businesswire.com/news/home/20240603799554/en/

Cory Pforzheimer
1-805-895-2281
cory.pforzheimer@intel.com