Tenstorrent Japan Event: Kimi K2.6 Inference Speeds Up 3x to 900 t/s/u

sloppenheimer · x · 2026-07-03

Tenstorrent hosted the TT-Deploy Japan event in Tokyo, announcing multiple AI inference acceleration achievements. Key data reveals that Moonshot AI's Kimi K2.6 achieved an inference throughput of 900 token/second/user on their hardware, which is 3x faster than before. This marks a significant appearance for Tenstorrent in the Japanese market and demonstrates the competitiveness of its inference acceleration chips in deploying mainstream Chinese LLMs.

Original post →

More from Infra

Infra channel →