China Telecom Releases Open-Source Xing4.0-29B-A4B Trained on Ascend
China Telecom Open-Sources Xing4.0-29B-A4B Agentic MoE Trained End-to-End on Ascend
The full training stack runs on domestic Ascend hardware rather than NVIDIA GPUs, making it a concrete example of China's compute self-sufficiency efforts at the model level. Developers can download the open weights from Hugging Face or ModelScope and experiment with an agentic MoE that needs only 4B active parameters per token. It also offers a direct comparison point against similarly sized open MoE models.
China Telecom AI released Xing4.0-29B-A4B, a 29B-parameter Mixture-of-Experts model with 4B active parameters and a 256K context window.
The model was trained end-to-end on Huawei Ascend NPUs using the MindSpore framework.It is designed for agentic workloads and has been published with open weights on Hugging Face and ModelScope.
China Telecom Open-Sources Xing4.0-29B-A4B Agentic MoE Trained End-to-End on Ascend
China Telecom AI released Xing4.0-29B-A4B, a 29B-parameter Mixture-of-Experts model with 4B active parameters and 256K context, trained end-to-end on Ascend NPUs with MindSpore and published with open weights on Hugging Face and ModelScope.
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include China Telecom, Xing4.0, Ascend, MindSpore.
Primary source verification: published directly by pandaily with first-party authority.
