Over the last 24 hours, the TEE-backed AI infrastructure at Phala has successfully processed an impressive 16.66 billion tokens to support various Confidential AI workloads.
Taking a closer look at the most utilized models during this period, DeepSeek V4 Flash led the group by accounting for 39.44% of the total volume. It was closely followed by GLM-5.2 at 26.48%, while Muse Glimmer 30B captured an 8.94% share.
You can dive into the details of the leading model by checking out Explore #1: https://phala.com/models/deepseek/deepseek-v4-flash-0731
Taking a closer look at the most utilized models during this period, DeepSeek V4 Flash led the group by accounting for 39.44% of the total volume. It was closely followed by GLM-5.2 at 26.48%, while Muse Glimmer 30B captured an 8.94% share.
You can dive into the details of the leading model by checking out Explore #1: https://phala.com/models/deepseek/deepseek-v4-flash-0731