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.
More from Infra
- Intel 10-Q points to 18A/14A progress and “potential significant external customers” — BenBajarin · 2026-07-27
- Moonshot’s Kimi K3 lands on Together with reserved throughput and 65% lower cost — togethercompute · 2026-07-27
- OpenAI may be hitting compute limits as Codex and ChatGPT Work jump from 2M to 10M users — JoshuaJBouw · 2026-07-27
- NVIDIA says Vera CPU is speeding up next-gen CPU and GPU design cycles — nordicinst · 2026-07-27
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- NVIDIA says Vera CPU lifted selected EDA workloads by up to 1.5x — NVIDIA Blog · 2026-07-27