Iluvatar CoreX Tiange 300 opens its first live machine demonstration to the media

On October 28, 2026, Iluvatar CoreX opened the Tiange 300 live machine demonstration to the media for the first time at a media open day. Phoenix Technology reported that the Tiange 300 generally outperformed the H200 in comparative tests on large language models such as GLM-5.3 as well as text-to-image and text-to-video scenarios; in an 8-card full-machine FP8-precision demonstration based on Qwen3-32B, the effective throughput per card reached 1.33 times that of the H100. A subsequent Leiphone report disclosed that in third-party testing, under a typical PD-disaggregated deployment, the Tiange 300's converted single-card end-to-end throughput reached 1.05 times that of the H200, and its MoE throughput in the 64K long-context scenario of GLM-5.3 was 1.15 times that of the H200; its software stack introduces Agents and Skills, and in a complete model service deployment case, the time from environment preparation to service availability was shortened from about one hour to about 20 minutes. The Tiange 300 was released in July 2026 at the World Artificial Intelligence Conference and is equipped with 144GB of memory.

AI-generated from public reports

1. Oct 28· 3 reports

   Iluvatar CoreX's Tiangai 300 opens its first in-person demonstration to the media

   Source:Phoenix Technology