Iluvatar claims Tiangai 300 GPU matches Nvidia’s H200 in AI workloads
Iluvatar CoreX, a Chinese AI chipmaker based in Shanghai, says its new Tiangai 300 GPU matches or outperforms Nvidia’s H200 in real-world AI tasks. In a live demo for Chinese media on Wednesday, the company showed the Tiangai 300 excelling in multimodal tasks like text-to-image and text-to-video generation using models such as Z.ai’s GLM-5.3. Benchmarks from state-backed Shanghai INESA found the…
Key points
- Tiangai 300 matches Nvidia’s H200 in AI workloads, per Iluvatar’s claims and state-backed benchmarks
- Achieved 1.05x throughput of H200 in text-to-image tasks, 1.33x in training Qwen3-32B models
- Iluvatar targets edge computing and aims to surpass Nvidia’s Rubin platform within two years
Model page: GLM 5.3 →
Chinese AI chipmaker Iluvatar CoreX says new GPU matches Nvidia’s H200 as chip gap closes
scmp.com · 29 October 2026
Loading the full article…
This text was published by scmp.com and written by Ann Cao. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Hardware & Compute
All →- OpenAI may purchase Google AI chips, report says · 4 src
- Alphabet introduces TPU 8t and 8i with lower AI chip costs · 1 src
- Bank of America says open-weight AI models boost Nvidia’s chip demand · 1 src
- $10,000 in AMD or Nvidia by 2030 yields very different returns, model predicts · 3 src
- Eclypsium and Nvidia team up to secure AI infrastructure firmware · 3 src
Comments
via GitHub Discussions