🔥36氪•Stalecollected in 26m
T-Head Unveils Zhenwu M890 AI Chip with 3x Performance
💡New high-performance AI chip from T-Head with 3x performance boost for large-scale training clusters.
⚡ 30-Second TL;DR
What Changed
Zhenwu M890 features 144GB memory and 800GB/s interconnect bandwidth.
Why It Matters
The M890 significantly boosts Alibaba's infrastructure capabilities for Agentic AI, providing a competitive alternative for high-performance computing clusters in the Chinese market.
What To Do Next
Evaluate the Zhenwu M890's specs for your large-scale model training workloads if you are operating within the Alibaba Cloud ecosystem.
Who should care:Enterprise & Security Teams
Key Points
- •Zhenwu M890 features 144GB memory and 800GB/s interconnect bandwidth.
- •Delivers 3x performance improvement over the Zhenwu 810E.
- •Supports diverse data precisions from FP32 to FP4 for training and inference.
- •Pairs with ICN Switch 1.0 for 64-card full-bandwidth cluster interconnects.
🧠 Deep Insight
Web-grounded analysis with 18 cited sources.
🔑 Enhanced Key Takeaways
- •The Zhenwu M890 is a core component of Alibaba's 'AI Golden Triangle' strategy, which integrates T-Head's proprietary chips with Alibaba Cloud's infrastructure and the Qwen large language model family to create a comprehensive AI supercomputing system.
- •The chip is specifically optimized for 'agentic AI workloads,' which are characterized by their demand for extensive working memory to retain context and high-speed communication capabilities for complex reasoning.
- •Alibaba Cloud has introduced a 128-card supernode server, named Pangu AL128, which incorporates the Zhenwu M890 and the ICN Switch 1.0, achieving communication latency as low as the hundred-nanosecond level for integrated computing.
- •T-Head has demonstrated significant market penetration, having delivered 560,000 Zhenwu units to over 400 enterprise customers across more than 20 industries as of May 2026.
- •The Zhenwu M890's predecessor, the Zhenwu 810E, was reported to offer performance comparable to Nvidia's China-compliant H20 accelerator and superior to the Nvidia A800, indicating T-Head's competitive standing in the domestic market.
📊 Competitor Analysis▸ Show
markdown
| Feature / Chip | T-Head Zhenwu M890 (2026) | T-Head Zhenwu 810E (2026) | Nvidia H20 (China-compliant) | Huawei Ascend 910B (2022) |
|---|---|---|---|---|
| Memory | 144GB | 96GB HBM2e | 96GB (implied) | Double on-chip memory of 910, HBM2e (specific capacity not detailed) |
| Interconnect B/W | 800GB/s | 700GB/s | 700GB/s (implied) | Higher bandwidth than 910 (specific value not detailed) |
| Performance | 3x Zhenwu 810E | Comparable to Nvidia H20, surpasses A800 | Comparable to Zhenwu 810E | Matches/surpasses Nvidia A100 in some tests, 80% A100 efficiency in LLM training, 20% better in others |
| Data Precision | FP32 to FP4 | Not specified | Not specified | FP16, INT8 (Ascend 910) |
| Manufacturing Process | Not specified | Not specified | Not specified | SMIC's 7nm fabrication process |
| Architecture | Proprietary parallel computing architecture | Proprietary parallel computing architecture | Not specified | DaVinci cores (25 active cores in 910B vs 32 in 910) |
| Pricing | Not available | Alibaba Cloud pricing increased 5-34% (March 2026) | Not available | Up to 40% lower cost than imported alternatives (for T-Head PPU generally) |
🛠️ Technical Deep Dive
- The Zhenwu M890 features 144GB of memory and 800GB/s interconnect bandwidth.
- It supports diverse data precisions ranging from FP32 down to FP4 for both training and inference tasks.
- The chip is integrated into Alibaba Cloud's new 128-card supernode server, known as Pangu AL128.
- The M890 pairs with the ICN Switch 1.0, which facilitates 64-card full-bandwidth cluster interconnects and reduces communication latency to the hundred-nanosecond level.
- Its predecessor, the Zhenwu 810E, was built on a proprietary parallel computing architecture and utilized in-house inter-chip interconnect technology, complemented by a fully self-developed software stack for end-to-end vertical integration.
🔮 Future ImplicationsAI analysis grounded in cited sources
Alibaba Cloud's market share in China's AI infrastructure will likely increase significantly.
With its proprietary Zhenwu M890 chip and a full-stack AI Cloud strategy, Alibaba is uniquely positioned to meet the escalating demand for AI compute in China, especially given ongoing global chip shortages and geopolitical pressures.
T-Head is likely to pursue an Initial Public Offering (IPO) in the near future.
Reports indicate that Alibaba is planning an IPO for its T-Head unit to secure substantial capital for further investments in AI infrastructure and to capitalize on the unit's growing market validation and strategic importance.
The development of domestic AI chips like Zhenwu M890 will accelerate China's technological self-reliance in advanced AI capabilities.
Alibaba's substantial investment in T-Head directly addresses the national imperative for domestic alternatives to advanced AI accelerators, driven by U.S. export controls and a strategic push for semiconductor self-sufficiency.
⏳ Timeline
2018-09
Alibaba establishes T-Head (Pingtouge) as its semiconductor subsidiary.
2019-09
Alibaba announces Hanguang 800, its first self-developed AI inference chip.
2025-09
T-Head develops a new series of AI accelerators (PPU), with performance comparable to Nvidia's H20 and A800 GPUs, deployed by China Unicom.
2026-01-29
T-Head officially unveils the Zhenwu 810E AI chip on its website, confirming performance comparable to Nvidia H20.
2026-03-20
T-Head's Zhenwu 810E GPU reaches large-scale production, with 470,000 units delivered as of February 2026.
2026-05-20
Alibaba's T-Head launches the Zhenwu M890 AI chip, offering 3x performance over its predecessor.
📎 Sources (18)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
📰
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: 36氪 ↗